2023
Class-Incremental Exemplar Compression for Class-Incremental Learning
Z. Luo, Y. Liu, B. Schiele and Q. Sun
36th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023), 2023
(Accepted/in press) Z. Luo, Y. Liu, B. Schiele and Q. Sun
36th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023), 2023
Neural Architecture Design and Robustness: A Dataset
S. Jung, J. Lukasik and M. Keuper
Eleventh International Conference on Learning Representations (ICLR 2023), 2023
(Accepted/in press) S. Jung, J. Lukasik and M. Keuper
Eleventh International Conference on Learning Representations (ICLR 2023), 2023
Abstract
Deep learning models have proven to be successful in a wide <br>range of machine learning tasks. Yet, they are often highly sensitive to <br>perturbations on the input data which can lead to incorrect decisions <br>with high confidence, hampering their deployment for practical <br>use-cases. Thus, finding architectures that are (more) robust against <br>perturbations has received much attention in recent years. Just like the <br>search for well-performing architectures in terms of clean accuracy, <br>this usually involves a tedious trial-and-error process with one <br>additional challenge: the evaluation of a network's robustness is <br>significantly more expensive than its evaluation for clean accuracy. <br>Thus, the aim of this paper is to facilitate better streamlined research <br>on architectural design choices with respect to their impact on <br>robustness as well as, for example, the evaluation of surrogate measures <br>for robustness. We therefore borrow one of the most commonly considered <br>search spaces for neural architecture search for image classification, <br>NAS-Bench-201, which contains a manageable size of 6466 non-isomorphic <br>network designs. We evaluate all these networks on a range of common <br>adversarial attacks and corruption types and introduce a database on <br>neural architecture design and robustness evaluations. We further <br>present three exemplary use cases of this dataset, in which we (i) <br>benchmark robustness measurements based on Jacobian and Hessian matrices <br>for their robustness predictability, (ii) perform neural architecture <br>search on robust accuracies, and (iii) provide an initial analysis of <br>how architectural design choices affect robustness. We find that <br>carefully crafting the topology of a network can have substantial impact <br>on its robustness, where networks with the same parameter count range in <br>mean adversarial robust accuracy from 20%-41%.
FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning
Y. Wang, H. Chen, Q. Heng, W. Hou, Y. Fan, Z. Wu, J. Wang, M. Savvides, T. Shinozaki, B. Raj, B. Schiele and X. Xie
Eleventh International Conference on Learning Representations (ICLR 2023), 2023
(Accepted/in press) Y. Wang, H. Chen, Q. Heng, W. Hou, Y. Fan, Z. Wu, J. Wang, M. Savvides, T. Shinozaki, B. Raj, B. Schiele and X. Xie
Eleventh International Conference on Learning Representations (ICLR 2023), 2023
Federated Incremental Semantic Segmentation
J. Dong, D. Zhang, Y. Cong, W. Cong, H. Ding and D. Dai
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023), 2023
(Accepted/in press) J. Dong, D. Zhang, Y. Cong, W. Cong, H. Ding and D. Dai
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023), 2023
MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation
L. Hoyer, D. Dai, H. Wang and L. Van Gool
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023), 2023
(Accepted/in press) L. Hoyer, D. Dai, H. Wang and L. Van Gool
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023), 2023
A Meta-Learning Approach to Predicting Performance and Data Requirements
A. Jain, G. Swaminathan, P. Favaro, H. Yang, A. Ravichandran, H. Harutyunyan, A. Achille, O. Dabeer, B. Schiele, A. Swaminathan and S. Soatto
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023), 2023
(Accepted/in press) A. Jain, G. Swaminathan, P. Favaro, H. Yang, A. Ravichandran, H. Harutyunyan, A. Achille, O. Dabeer, B. Schiele, A. Swaminathan and S. Soatto
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023), 2023
Self-Supervised Pre-Training With Masked Shape Prediction for 3D Scene Understanding
L. Jiang, Z. Yang, S. Shi, V. Golyanik, D. Dai and B. Schiele
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023), 2023
(Accepted/in press) L. Jiang, Z. Yang, S. Shi, V. Golyanik, D. Dai and B. Schiele
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023), 2023
Continual Detection Transformer for Incremental Object Detection
Y. Liu, B. Schiele, A. Vedaldi and C. Rupprecht
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023), 2023
(Accepted/in press) Y. Liu, B. Schiele, A. Vedaldi and C. Rupprecht
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023), 2023
DSVT: Dynamic Sparse Voxel Transformer With Rotated Sets
H. Wang, C. Shi, S. Shi, M. Lei, S. Wang, D. He, B. Schiele and L. Wang
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023), 2023
(Accepted/in press) H. Wang, C. Shi, S. Shi, M. Lei, S. Wang, D. He, B. Schiele and L. Wang
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023), 2023
Visibility Aware Human-Object Interaction Tracking from Single RGB Camera
X. Xie, B. L. Bhatnagar and G. Pons-Moll
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023), 2023
(Accepted/in press) X. Xie, B. L. Bhatnagar and G. Pons-Moll
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023), 2023
A Deeper Look into DeepCap
M. Habermann, W. Xu, M. Zollhöfer, G. Pons-Moll and C. Theobalt
IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 45, Number 4, 2023
M. Habermann, W. Xu, M. Zollhöfer, G. Pons-Moll and C. Theobalt
IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 45, Number 4, 2023
Abstract
Human performance capture is a highly important computer vision problem with<br>many applications in movie production and virtual/augmented reality. Many<br>previous performance capture approaches either required expensive multi-view<br>setups or did not recover dense space-time coherent geometry with<br>frame-to-frame correspondences. We propose a novel deep learning approach for<br>monocular dense human performance capture. Our method is trained in a weakly<br>supervised manner based on multi-view supervision completely removing the need<br>for training data with 3D ground truth annotations. The network architecture is<br>based on two separate networks that disentangle the task into a pose estimation<br>and a non-rigid surface deformation step. Extensive qualitative and<br>quantitative evaluations show that our approach outperforms the state of the<br>art in terms of quality and robustness. This work is an extended version of<br>DeepCap where we provide more detailed explanations, comparisons and results as<br>well as applications.<br>
Higher-Order Multicuts for Geometric Model Fitting and Motion Segmentation
E. Levinkov, A. Kardoost, B. Andres and M. Keuper
IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 45, Number 1, 2023
E. Levinkov, A. Kardoost, B. Andres and M. Keuper
IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 45, Number 1, 2023
Abstract
Minimum cost lifted multicut problem is a generalization of the multicut problem and is a means to optimizing a decomposition of a graph w.r.t. both positive and negative edge costs. Its main advantage is that multicut-based formulations do not require the number of components given a priori; instead, it is deduced from the solution. However, the standard multicut cost function is limited to pairwise relationships between nodes, while several important applications either require or can benefit from a higher-order cost function, i.e. hyper-edges. In this paper, we propose a pseudo-boolean formulation for a multiple model fitting problem. It is based on a formulation of any-order minimum cost lifted multicuts, which allows to partition an undirected graph with pairwise connectivity such as to minimize costs defined over any set of hyper-edges. As the proposed formulation is NP-hard and the branch-and-bound algorithm is too slow in practice, we propose an efficient local search algorithm for inference into resulting problems. We demonstrate versatility and effectiveness of our approach in several applications: geometric multiple model fitting, homography and motion estimation, motion segmentation.
Random and Adversarial Bit Error Robustness: Energy-Efficient and Secure DNN Accelerators
D. Stutz, N. Chandramoorthy, M. Hein and B. Schiele
IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 45, Number 3, 2023
D. Stutz, N. Chandramoorthy, M. Hein and B. Schiele
IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 45, Number 3, 2023
Urban Scene Semantic Segmentation With Low-Cost Coarse Annotation
A. Das, Y. Xian, Y. He, Z. Akata and B. Schiele
2023 IEEE Winter Conference on Applications of Computer Vision (WACV 2023), 2023
A. Das, Y. Xian, Y. He, Z. Akata and B. Schiele
2023 IEEE Winter Conference on Applications of Computer Vision (WACV 2023), 2023
Intra-Source Style Augmentation for Improved Domain Generalization
Y. Li, D. Zhang, M. Keuper and A. Khoreva
2023 IEEE Winter Conference on Applications of Computer Vision (WACV 2023), 2023
Y. Li, D. Zhang, M. Keuper and A. Khoreva
2023 IEEE Winter Conference on Applications of Computer Vision (WACV 2023), 2023
Revisiting Consistency Regularization for Semi-supervised Learning
Y. Fan, A. Kukleva, D. Dai and B. Schiele
International Journal of Computer Vision, Volume 131, 2023
Y. Fan, A. Kukleva, D. Dai and B. Schiele
International Journal of Computer Vision, Volume 131, 2023
Improving Semi-Supervised and Domain-Adaptive Semantic Segmentation with Self-Supervised Depth Estimation
L. Hoyer, D. Dai, Q. Wang, Y. Chen and L. Van Gool
International Journal of Computer Vision, 2023
L. Hoyer, D. Dai, Q. Wang, Y. Chen and L. Van Gool
International Journal of Computer Vision, 2023
3D Object Detection for Autonomous Driving: A Comprehensive Survey
J. Mao, S. Shi, X. Wang and H. Li
International Journal of Computer Vision, 2023
J. Mao, S. Shi, X. Wang and H. Li
International Journal of Computer Vision, 2023
Online Hyperparameter Optimization for Class-Incremental Learning
Y. Liu, Y. Li, B. Schiele and Q. Sun
Proceedings of the 37th AAAI Conference on Artificial Intelligence, 2023
(Accepted/in press) Y. Liu, Y. Li, B. Schiele and Q. Sun
Proceedings of the 37th AAAI Conference on Artificial Intelligence, 2023
Joint Self-Supervised Image-Volume Representation Learning with Intra-Inter Contrastive Clustering
D. M. H. Nguyen, H. Nguyen, M. T. N. Truong, T. Cao, B. T. Nguyen, N. Ho, P. Swoboda, S. Albarqouni, P. Xie and D. Sonntag
Proceedings of the 37th AAAI Conference on Artificial Intelligence, 2023
(Accepted/in press) D. M. H. Nguyen, H. Nguyen, M. T. N. Truong, T. Cao, B. T. Nguyen, N. Ho, P. Swoboda, S. Albarqouni, P. Xie and D. Sonntag
Proceedings of the 37th AAAI Conference on Artificial Intelligence, 2023
Learning from Imperfect Data Incremental Learning and Few-shot Learning
Y. Liu
PhD Thesis, Universität des Saarlandes, 2023
Y. Liu
PhD Thesis, Universität des Saarlandes, 2023
2022
Cross-Modal Fusion Distillation for Fine-Grained Sketch-Based Image Retrieval
A. Chaudhuri, M. Mancini, Y. Chen, Z. Akata and A. Dutta
33rd British Machine Vision Conference (BMVC 2022), 2022
A. Chaudhuri, M. Mancini, Y. Chen, Z. Akata and A. Dutta
33rd British Machine Vision Conference (BMVC 2022), 2022
Distilling Knowledge from Self-Supervised Teacher by Embedding Graph Alignment
Y. Ma, Y. Chen and Z. Akata
33rd British Machine Vision Conference (BMVC 2022), 2022
Y. Ma, Y. Chen and Z. Akata
33rd British Machine Vision Conference (BMVC 2022), 2022
SP-ViT: Learning 2D Spatial Priors for Vision Transformers
Y. Zhou, W. Xiang, C. Li, B. Wang, X. Wei, L. Zhang, M. Keuper and X. Hua
33rd British Machine Vision Conference (BMVC 2022), 2022
Y. Zhou, W. Xiang, C. Li, B. Wang, X. Wei, L. Zhang, M. Keuper and X. Hua
33rd British Machine Vision Conference (BMVC 2022), 2022
Relational Proxies: Emergent Relationships as Fine-Grained Discriminators
A. Chaudhuri, M. Mancini, Z. Akata and A. Dutta
Advances in Neural Information Processing Systems 35 (NeurIPS 2022), 2022
A. Chaudhuri, M. Mancini, Z. Akata and A. Dutta
Advances in Neural Information Processing Systems 35 (NeurIPS 2022), 2022
Robust Models are less Over-Confident
J. Grabinski, P. Gavrikov, J. Keuper and M. Keuper
Advances in Neural Information Processing Systems 35 (NeurIPS 2022), 2022
J. Grabinski, P. Gavrikov, J. Keuper and M. Keuper
Advances in Neural Information Processing Systems 35 (NeurIPS 2022), 2022
Trading off Image Quality for Robustness is not Necessary with Regularized Deterministic Autoencoders
A. Saseendran, K. Skubch and M. Keuper
Advances in Neural Information Processing Systems 35 (NeurIPS 2022), 2022
A. Saseendran, K. Skubch and M. Keuper
Advances in Neural Information Processing Systems 35 (NeurIPS 2022), 2022
Motion Transformer with Global Intention Localization and Local Movement Refinement
S. Shi, L. Jiang, D. Dai and B. Schiele
Advances in Neural Information Processing Systems 35 (NeurIPS 2022), 2022
S. Shi, L. Jiang, D. Dai and B. Schiele
Advances in Neural Information Processing Systems 35 (NeurIPS 2022), 2022
CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds
H. Wang, L. Ding, S. Dong, S. Shi, A. Li, J. Li, Z. Li and L. Wang
Advances in Neural Information Processing Systems 35 (NeurIPS 2022), 2022
H. Wang, L. Ding, S. Dong, S. Shi, A. Li, J. Li, Z. Li and L. Wang
Advances in Neural Information Processing Systems 35 (NeurIPS 2022), 2022
USB: A Unified Semi-supervised Learning Benchmark for Classification
Y. Wang, H. Chen, Y. Fan, W. Sun, R. Tao, W. Hou, R. Wang, L. Yang, Z. Zhou, L.-Z. Guo, H. Qi, Z. Wu, Y.-F. Li, S. Nakamura, W. Ye, M. Savvides, B. Raj, T. Shinozaki, B. Schiele, J. Wang, X. Xie and Y. Zhang
Advances in Neural Information Processing Systems 35 (NeurIPS 2022), 2022
Y. Wang, H. Chen, Y. Fan, W. Sun, R. Tao, W. Hou, R. Wang, L. Yang, Z. Zhou, L.-Z. Guo, H. Qi, Z. Wu, Y.-F. Li, S. Nakamura, W. Ye, M. Savvides, B. Raj, T. Shinozaki, B. Schiele, J. Wang, X. Xie and Y. Zhang
Advances in Neural Information Processing Systems 35 (NeurIPS 2022), 2022
Towards Efficient 3D Object Detection with Knowledge Distillation
J. Yang, S. Shi, R. Ding, Z. Wang and X. Qi
Advances in Neural Information Processing Systems 35 (NeurIPS 2022), 2022
J. Yang, S. Shi, R. Ding, Z. Wang and X. Qi
Advances in Neural Information Processing Systems 35 (NeurIPS 2022), 2022
Abstracting Sketches Through Simple Primitives
S. Alaniz, M. Mancini, A. Dutta, D. Marcos and Z. Akata
Computer Vision -- ECCV 2022, 2022
S. Alaniz, M. Mancini, A. Dutta, D. Marcos and Z. Akata
Computer Vision -- ECCV 2022, 2022
MPPNet: Multi-frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection
X. Chen, S. Shi, B. Zhu, K. C. Cheung, H. Xu and H. Li
Computer Vision -- ECCV 2022, 2022
X. Chen, S. Shi, B. Zhu, K. C. Cheung, H. Xu and H. Li
Computer Vision -- ECCV 2022, 2022
Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation using Bounding Boxes
J. Chibane, F. Engelmann, A. T. Tran and G. Pons-Moll
Computer Vision -- ECCV 2022, 2022
J. Chibane, F. Engelmann, A. T. Tran and G. Pons-Moll
Computer Vision -- ECCV 2022, 2022
Learned Vertex Descent: A New Direction for 3D Human Model Fitting
E. Corona, G. Pons-Moll, G. Alenyà and F. Moreno-Noguer
Computer Vision -- ECCV 2022, 2022
E. Corona, G. Pons-Moll, G. Alenyà and F. Moreno-Noguer
Computer Vision -- ECCV 2022, 2022
DODA: Data-Oriented Sim-to-Real Domain Adaptation for 3D Semantic Segmentation
R. Ding, J. Yang, L. Jiang and X. Qi
Computer Vision -- ECCV 2022, 2022
R. Ding, J. Yang, L. Jiang and X. Qi
Computer Vision -- ECCV 2022, 2022
Class-Agnostic Object Counting Robust to Intraclass Diversity
S. Gong, S. Zhang, J. Yang, D. Dai and B. Schiele
Computer Vision -- ECCV 2022, 2022
S. Gong, S. Zhang, J. Yang, D. Dai and B. Schiele
Computer Vision -- ECCV 2022, 2022
FrequencyLowCut Pooling - Plug & Play against Catastrophic Overfitting
J. Grabinski, S. Jung, J. Keuper and M. Keuper
Computer Vision -- ECCV 2022, 2022
J. Grabinski, S. Jung, J. Keuper and M. Keuper
Computer Vision -- ECCV 2022, 2022
Improving Robustness by Enhancing Weak Subnets
Y. Guo, D. Stutz and B. Schiele
Computer Vision -- ECCV 2022, 2022
Y. Guo, D. Stutz and B. Schiele
Computer Vision -- ECCV 2022, 2022
A Comparative Study of Graph Matching Algorithms in Computer Vision
S. Haller, L. Feineis, L. Hutschenreiter, F. Bernard, C. Rother, D. Kainmüller, P. Swoboda and B. Savchynskyy
Computer Vision -- ECCV 2022, 2022
S. Haller, L. Feineis, L. Hutschenreiter, F. Bernard, C. Rother, D. Kainmüller, P. Swoboda and B. Savchynskyy
Computer Vision -- ECCV 2022, 2022
Skeleton-Free Pose Transfer for Stylized 3D Characters
Z. Liao, J. Yang, J. Saito, G. Pons-Moll and Y. Zhou
Computer Vision -- ECCV 2022, 2022
Z. Liao, J. Yang, J. Saito, G. Pons-Moll and Y. Zhou
Computer Vision -- ECCV 2022, 2022
CycDA: Unsupervised Cycle Domain Adaptation to Learn from Image to Video
W. Lin, A. Kukleva, K. Sun, H. Possegger, H. Kuehne and H. Bischof
Computer Vision -- ECCV 2022, 2022
W. Lin, A. Kukleva, K. Sun, H. Possegger, H. Kuehne and H. Bischof
Computer Vision -- ECCV 2022, 2022
Learning Where To Look - Generative NAS is Surprisingly Efficient
J. Lukasik, S. Jung and M. Keuper
Computer Vision -- ECCV 2022, 2022
J. Lukasik, S. Jung and M. Keuper
Computer Vision -- ECCV 2022, 2022
Temporal and Cross-modal Attention for Audio-Visual Zero-Shot Learning
O.-B. Mercea, T. Hummel, A. S. Koepke and Z. Akata
Computer Vision -- ECCV 2022, 2022
O.-B. Mercea, T. Hummel, A. S. Koepke and Z. Akata
Computer Vision -- ECCV 2022, 2022
HULC: 3D HUman Motion Capture with Pose Manifold SampLing and Dense Contact Guidance
S. Shimada, V. Golyanik, Z. Li, P. Pérez, W. Xu and C. Theobalt
Computer Vision -- ECCV 2022, 2022
S. Shimada, V. Golyanik, Z. Li, P. Pérez, W. Xu and C. Theobalt
Computer Vision -- ECCV 2022, 2022
Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fields
G. Tiwari, D. Antic, J. E. Lenssen, N. Sarafianos, T. Tung and G. Pons-Moll
Computer Vision -- ECCV 2022, 2022
G. Tiwari, D. Antic, J. E. Lenssen, N. Sarafianos, T. Tung and G. Pons-Moll
Computer Vision -- ECCV 2022, 2022
CHORE: Contact, Human and Object Reconstruction from a Single RGB Image
X. Xie, B. L. Bhatnagar and G. Pons-Moll
Computer Vision -- ECCV 2022, 2022
X. Xie, B. L. Bhatnagar and G. Pons-Moll
Computer Vision -- ECCV 2022, 2022
COUCH: Towards Controllable Human-Chair Interactions
X. Zhang, B. L. Bhatnagar, S. Starke, V. Guzov and G. Pons-Moll
Computer Vision -- ECCV 2022, 2022
X. Zhang, B. L. Bhatnagar, S. Starke, V. Guzov and G. Pons-Moll
Computer Vision -- ECCV 2022, 2022
TOCH: Spatio-Temporal Object Correspondence to Hand for Motion Refinement
K. Zhou, B. L. Bhatnagar, J. E. Lenssen and G. Pons-Moll
Computer Vision -- ECCV 2022, 2022
K. Zhou, B. L. Bhatnagar, J. E. Lenssen and G. Pons-Moll
Computer Vision -- ECCV 2022, 2022
Advancing Translational Research in Neuroscience through Multi-task Learning
H. Cao, X. Hong, H. Tost, A. Meyer-Lindenberg and E. Schwarz
Frontiers in Psychiatry, Volume 13, 2022
H. Cao, X. Hong, H. Tost, A. Meyer-Lindenberg and E. Schwarz
Frontiers in Psychiatry, Volume 13, 2022
Semantic Image Synthesis with Semantically Coupled VQ-Model
S. Alaniz, T. Hummel and Z. Akata
ICLR Workshop on Deep Generative Models for Highly Structured Data (ICLR 2022 DGM4HSD), 2022
S. Alaniz, T. Hummel and Z. Akata
ICLR Workshop on Deep Generative Models for Highly Structured Data (ICLR 2022 DGM4HSD), 2022
RAMA: A Rapid Multicut Algorithm on GPU
A. Abbas and P. Swoboda
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
A. Abbas and P. Swoboda
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
FastDOG: Fast Discrete Optimization on GPU
A. Abbas and P. Swoboda
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
A. Abbas and P. Swoboda
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
BEHAVE: Dataset and Method for Tracking Human Object Interactions
B. L. Bhatnagar, X. Xie, I. Petrov, C. Sminchisescu, C. Theobalt and G. Pons-Moll
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
B. L. Bhatnagar, X. Xie, I. Petrov, C. Sminchisescu, C. Theobalt and G. Pons-Moll
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
B-cos Networks: Alignment is All We Need for Interpretability
M. Böhle, M. Fritz and B. Schiele
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
M. Böhle, M. Fritz and B. Schiele
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
Pix2NeRF: Unsupervised Conditional Pi-GAN for Single Image to Neural Radiance Fields Translation
S. Cai, A. Obukhov, D. Dai and L. Van Gool
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
S. Cai, A. Obukhov, D. Dai and L. Van Gool
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
Decoupling Zero-Shot Semantic Segmentation
J. Ding, N. Xue, G.-S. Xia and D. Dai
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
J. Ding, N. Xue, G.-S. Xia and D. Dai
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
Abstract
Zero-shot semantic segmentation (ZS3) aims to segment the novel categories<br>that have not been seen in the training. Existing works formulate ZS3 as a<br>pixel-level zero-shot classification problem, and transfer semantic knowledge<br>from seen classes to unseen ones with the help of language models pre-trained<br>only with texts. While simple, the pixel-level ZS3 formulation shows the<br>limited capability to integrate vision-language models that are often<br>pre-trained with image-text pairs and currently demonstrate great potential for<br>vision tasks. Inspired by the observation that humans often perform<br>segment-level semantic labeling, we propose to decouple the ZS3 into two<br>sub-tasks: 1) a class-agnostic grouping task to group the pixels into segments.<br>2) a zero-shot classification task on segments. The former sub-task does not<br>involve category information and can be directly transferred to group pixels<br>for unseen classes. The latter subtask performs at segment-level and provides a<br>natural way to leverage large-scale vision-language models pre-trained with<br>image-text pairs (e.g. CLIP) for ZS3. Based on the decoupling formulation, we<br>propose a simple and effective zero-shot semantic segmentation model, called<br>ZegFormer, which outperforms the previous methods on ZS3 standard benchmarks by<br>large margins, e.g., 35 points on the PASCAL VOC and 3 points on the COCO-Stuff<br>in terms of mIoU for unseen classes. Code will be released at<br>https://github.com/dingjiansw101/ZegFormer.<br>
PoseTrack21: A Dataset for Person Search, Multi-Object Tracking and Multi-Person Pose Tracking
A. Doering, D. Chen, S. Zhang, B. Schiele and J. Gall
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
A. Doering, D. Chen, S. Zhang, B. Schiele and J. Gall
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
CoSSL: Co-Learning of Representation and Classifier for Imbalanced Semi-Supervised Learning
Y. Fan, D. Dai and B. Schiele
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
Y. Fan, D. Dai and B. Schiele
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
Abstract
In this paper, we propose a novel co-learning framework (CoSSL) with<br>decoupled representation learning and classifier learning for imbalanced SSL.<br>To handle the data imbalance, we devise Tail-class Feature Enhancement (TFE)<br>for classifier learning. Furthermore, the current evaluation protocol for<br>imbalanced SSL focuses only on balanced test sets, which has limited<br>practicality in real-world scenarios. Therefore, we further conduct a<br>comprehensive evaluation under various shifted test distributions. In<br>experiments, we show that our approach outperforms other methods over a large<br>range of shifted distributions, achieving state-of-the-art performance on<br>benchmark datasets ranging from CIFAR-10, CIFAR-100, ImageNet, to Food-101. Our<br>code will be made publicly available.<br>
Bi-level Alignment for Cross-Domain Crowd Counting
S. Gong, S. Zhang, J. Yang, D. Dai and B. Schiele
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
S. Gong, S. Zhang, J. Yang, D. Dai and B. Schiele
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
LiDAR Snowfall Simulation for Robust 3D Object Detection
M. Hahner, C. Sakaridis, M. Bijelic, F. Heide, F. Yu, D. Dai and L. Van Gool
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
M. Hahner, C. Sakaridis, M. Bijelic, F. Heide, F. Yu, D. Dai and L. Van Gool
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation
L. Hoyer, D. Dai and L. Van Gool
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
L. Hoyer, D. Dai and L. Van Gool
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
Abstract
As acquiring pixel-wise annotations of real-world images for semantic<br>segmentation is a costly process, a model can instead be trained with more<br>accessible synthetic data and adapted to real images without requiring their<br>annotations. This process is studied in unsupervised domain adaptation (UDA).<br>Even though a large number of methods propose new adaptation strategies, they<br>are mostly based on outdated network architectures. As the influence of recent<br>network architectures has not been systematically studied, we first benchmark<br>different network architectures for UDA and then propose a novel UDA method,<br>DAFormer, based on the benchmark results. The DAFormer network consists of a<br>Transformer encoder and a multi-level context-aware feature fusion decoder. It<br>is enabled by three simple but crucial training strategies to stabilize the<br>training and to avoid overfitting DAFormer to the source domain: While the Rare<br>Class Sampling on the source domain improves the quality of pseudo-labels by<br>mitigating the confirmation bias of self-training towards common classes, the<br>Thing-Class ImageNet Feature Distance and a learning rate warmup promote<br>feature transfer from ImageNet pretraining. DAFormer significantly improves the<br>state-of-the-art performance by 10.8 mIoU for GTA->Cityscapes and 5.4 mIoU for<br>Synthia->Cityscapes and enables learning even difficult classes such as train,<br>bus, and truck well. The implementation is available at<br>https://github.com/lhoyer/DAFormer.<br>
Large Loss Matters in Weakly Supervised Multi-Label Classification
Y. Kim, J. M. Kim, Z. Akata and J. Lee
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
Y. Kim, J. M. Kim, Z. Akata and J. Lee
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
Stratified Transformer for 3D Point Cloud Segmentation
X. Lai, J. Liu, L. Jiang, L. Wang, H. Zhao, S. Liu, X. Qi and J. Jia
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
X. Lai, J. Liu, L. Jiang, L. Wang, H. Zhao, S. Liu, X. Qi and J. Jia
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
Both Style and Fog Matter: Cumulative Domain Adaptation for Semantic Foggy Scene Understanding
X. Ma, Z. Wang, Y. Zhan, Y. Zheng, Z. Wang, D. Dai and C.-W. Lin
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
X. Ma, Z. Wang, Y. Zhan, Y. Zheng, Z. Wang, D. Dai and C.-W. Lin
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
Abstract
Although considerable progress has been made in semantic scene understanding<br>under clear weather, it is still a tough problem under adverse weather<br>conditions, such as dense fog, due to the uncertainty caused by imperfect<br>observations. Besides, difficulties in collecting and labeling foggy images<br>hinder the progress of this field. Considering the success in semantic scene<br>understanding under clear weather, we think it is reasonable to transfer<br>knowledge learned from clear images to the foggy domain. As such, the problem<br>becomes to bridge the domain gap between clear images and foggy images. Unlike<br>previous methods that mainly focus on closing the domain gap caused by fog --<br>defogging the foggy images or fogging the clear images, we propose to alleviate<br>the domain gap by considering fog influence and style variation simultaneously.<br>The motivation is based on our finding that the style-related gap and the<br>fog-related gap can be divided and closed respectively, by adding an<br>intermediate domain. Thus, we propose a new pipeline to cumulatively adapt<br>style, fog and the dual-factor (style and fog). Specifically, we devise a<br>unified framework to disentangle the style factor and the fog factor<br>separately, and then the dual-factor from images in different domains.<br>Furthermore, we collaborate the disentanglement of three factors with a novel<br>cumulative loss to thoroughly disentangle these three factors. Our method<br>achieves the state-of-the-art performance on three benchmarks and shows<br>generalization ability in rainy and snowy scenes.<br>
Audio-visual Generalised Zero-shot Learning with Cross-modal Attention and Language
O.-B. Mercea, L. Riesch, A. S. Koepke and Z. Akata
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
O.-B. Mercea, L. Riesch, A. S. Koepke and Z. Akata
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
LMGP: Lifted Multicut Meets Geometry Projections for Multi-Camera Multi-Object Tracking
D. H. M. Nguyen, R. Henschel, B. Rosenhahn, D. Sonntag and P. Swoboda
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
D. H. M. Nguyen, R. Henschel, B. Rosenhahn, D. Sonntag and P. Swoboda
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
Abstract
Multi-Camera Multi-Object Tracking is currently drawing attention in the<br>computer vision field due to its superior performance in real-world<br>applications such as video surveillance with crowded scenes or in vast space.<br>In this work, we propose a mathematically elegant multi-camera multiple object<br>tracking approach based on a spatial-temporal lifted multicut formulation. Our<br>model utilizes state-of-the-art tracklets produced by single-camera trackers as<br>proposals. As these tracklets may contain ID-Switch errors, we refine them<br>through a novel pre-clustering obtained from 3D geometry projections. As a<br>result, we derive a better tracking graph without ID switches and more precise<br>affinity costs for the data association phase. Tracklets are then matched to<br>multi-camera trajectories by solving a global lifted multicut formulation that<br>incorporates short and long-range temporal interactions on tracklets located in<br>the same camera as well as inter-camera ones. Experimental results on the<br>WildTrack dataset yield near-perfect result, outperforming state-of-the-art<br>trackers on Campus while being on par on the PETS-09 dataset. We will make our<br>implementations available upon acceptance of the paper.<br>
Towards Better Understanding Attribution Methods
S. Rao, M. Böhle and B. Schiele
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
S. Rao, M. Böhle and B. Schiele
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
A Scalable Combinatorial Solver for Elastic Geometrically Consistent 3D Shape Matching
P. Roetzer, P. Swoboda, D. Cremers and F. Bernard
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
P. Roetzer, P. Swoboda, D. Cremers and F. Bernard
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation
T. Sun, M. Segù, J. Postels, Y. Wang, L. Van Gool, B. Schiele, F. Tombari and F. Yu
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
T. Sun, M. Segù, J. Postels, Y. Wang, L. Van Gool, B. Schiele, F. Tombari and F. Yu
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
Generalized Few-shot Semantic Segmentation
Z. Tian, X. Lai, L. Jiang, S. Liu, M. Shu, H. Zhao and J. Jia
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
Z. Tian, X. Lai, L. Jiang, S. Liu, M. Shu, H. Zhao and J. Jia
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
Scribble-Supervised LiDAR Semantic Segmentation
O. Unal, D. Dai and L. Van Gool
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
O. Unal, D. Dai and L. Van Gool
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
Sound and Visual Representation Learning with Multiple Pretraining Tasks
A. B. Vasudevan, D. Dai and L. Van Gool
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
A. B. Vasudevan, D. Dai and L. Van Gool
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
RBGNet: Ray-based Grouping for 3D Object Detection
H. Wang, S. Shi, Z. Yang, R. Fang, Q. Qian, H. Li, B. Schiele and L. Wang
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
H. Wang, S. Shi, Z. Yang, R. Fang, Q. Qian, H. Li, B. Schiele and L. Wang
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
Continual Test-Time Domain Adaptation
Q. Wang, O. Fink, L. Van Gool and D. Dai
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
Q. Wang, O. Fink, L. Van Gool and D. Dai
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
VGSE: Visually-Grounded Semantic Embeddings for Zero-Shot Learning
W. Xu, Y. Xian, J. Wang, B. Schiele and Z. Akata
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
W. Xu, Y. Xian, J. Wang, B. Schiele and Z. Akata
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
A Unified Query-based Paradigm for Point Cloud Understanding
Z. Yang, L. Jiang, Y. Sun, B. Schiele and J. Jia
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
Z. Yang, L. Jiang, Y. Sun, B. Schiele and J. Jia
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
Adiabatic Quantum Computing for Multi Object Tracking
J.-N. Zaech, A. Liniger, M. Danelljan, D. Dai and L. Van Gool
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
J.-N. Zaech, A. Liniger, M. Danelljan, D. Dai and L. Van Gool
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022
Semi-Supervised and Unsupervised Deep Visual Learning: A Survey
Y. Chen, M. Mancini, X. Zhu and Z. Akata
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022
Y. Chen, M. Mancini, X. Zhu and Z. Akata
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022
MoCapDeform: Monocular 3D Human Motion Capture in Deformable Scenes
Z. Li, S. Shimada, B. Schiele, C. Theobalt and V. Golyanik
International Conference on 3D Vision, 2022
Z. Li, S. Shimada, B. Schiele, C. Theobalt and V. Golyanik
International Conference on 3D Vision, 2022
Abstract
3D human motion capture from monocular RGB images respecting interactions of<br>a subject with complex and possibly deformable environments is a very<br>challenging, ill-posed and under-explored problem. Existing methods address it<br>only weakly and do not model possible surface deformations often occurring when<br>humans interact with scene surfaces. In contrast, this paper proposes<br>MoCapDeform, i.e., a new framework for monocular 3D human motion capture that<br>is the first to explicitly model non-rigid deformations of a 3D scene for<br>improved 3D human pose estimation and deformable environment reconstruction.<br>MoCapDeform accepts a monocular RGB video and a 3D scene mesh aligned in the<br>camera space. It first localises a subject in the input monocular video along<br>with dense contact labels using a new raycasting based strategy. Next, our<br>human-environment interaction constraints are leveraged to jointly optimise<br>global 3D human poses and non-rigid surface deformations. MoCapDeform achieves<br>superior accuracy than competing methods on several datasets, including our<br>newly recorded one with deforming background scenes.<br>
PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection
S. Shi, L. Jiang, J. Deng, Z. Wang, C. Guo, J. Shi, X. Wang and H. Li
International Journal of Computer Vision, Volume 131, 2022
S. Shi, L. Jiang, J. Deng, Z. Wang, C. Guo, J. Shi, X. Wang and H. Li
International Journal of Computer Vision, Volume 131, 2022
OASIS: Only Adversarial Supervision for Semantic Image Synthesis
V. Sushko, E. Schönfeld, D. Zhang, J. Gall, B. Schiele and A. Khoreva
International Journal of Computer Vision, Volume 130, 2022
V. Sushko, E. Schönfeld, D. Zhang, J. Gall, B. Schiele and A. Khoreva
International Journal of Computer Vision, Volume 130, 2022
Attribute Prototype Network for Any-Shot Learning
W. Xu, Y. Xian, J. Wang, B. Schiele and Z. Akata
International Journal of Computer Vision, Volume 130, 2022
W. Xu, Y. Xian, J. Wang, B. Schiele and Z. Akata
International Journal of Computer Vision, Volume 130, 2022
Aliasing and Adversarial Robust Generalization of CNNs
J. Grabinski, J. Keuper and M. Keuper
Machine Learning, Volume 111, 2022
J. Grabinski, J. Keuper and M. Keuper
Machine Learning, Volume 111, 2022
Learning to solve Minimum Cost Multicuts efficiently using Edge-Weighted Graph Convolutional Neural Networks
S. Jung and M. Keuper
Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2022), 2022
S. Jung and M. Keuper
Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2022), 2022
Abstract
The minimum cost multicut problem is the NP-hard/APX-hard combinatorial<br>optimization problem of partitioning a real-valued edge-weighted graph such as<br>to minimize the total cost of the partition. While graph convolutional neural<br>networks (GNN) have proven to be promising in the context of combinatorial<br>optimization, most of them are only tailored to or tested on positive-valued<br>edge weights, i.e. they do not comply to the nature of the multicut problem. We<br>therefore adapt various GNN architectures including Graph Convolutional<br>Networks, Signed Graph Convolutional Networks and Graph Isomorphic Networks to<br>facilitate the efficient encoding of real-valued edge costs. Moreover, we<br>employ a reformulation of the multicut ILP constraints to a polynomial program<br>as loss function that allows to learn feasible multicut solutions in a scalable<br>way. Thus, we provide the first approach towards end-to-end trainable<br>multicuts. Our findings support that GNN approaches can produce good solutions<br>in practice while providing lower computation times and largely improved<br>scalability compared to LP solvers and optimized heuristics, especially when<br>considering large instances.<br>
Impact of Realistic Properties of the Point Spread Function on Classification Tasks to Reveal a Possible Distribution Shift
P. Müller, A. Braun and M. Keuper
NeurIPS 2022 Workshop on Distribution Shifts: Connecting Methods and Applications (NeurIPS 2022 Workshop DistShift), 2022
P. Müller, A. Braun and M. Keuper
NeurIPS 2022 Workshop on Distribution Shifts: Connecting Methods and Applications (NeurIPS 2022 Workshop DistShift), 2022
Optimizing Edge Detection for Image Segmentation with Multicut Penalties
S. Jung, S. Ziegler, A. Kardoost and M. Keuper
Pattern Recognition (DAGM GCPR 2022), 2022
S. Jung, S. Ziegler, A. Kardoost and M. Keuper
Pattern Recognition (DAGM GCPR 2022), 2022
Abstract
The Minimum Cost Multicut Problem (MP) is a popular way for obtaining a graph<br>decomposition by optimizing binary edge labels over edge costs. While the<br>formulation of a MP from independently estimated costs per edge is highly<br>flexible and intuitive, solving the MP is NP-hard and time-expensive. As a<br>remedy, recent work proposed to predict edge probabilities with awareness to<br>potential conflicts by incorporating cycle constraints in the prediction<br>process. We argue that such formulation, while providing a first step towards<br>end-to-end learnable edge weights, is suboptimal, since it is built upon a<br>loose relaxation of the MP. We therefore propose an adaptive CRF that allows to<br>progressively consider more violated constraints and, in consequence, to issue<br>solutions with higher validity. Experiments on the BSDS500 benchmark for<br>natural image segmentation as well as on electron microscopic recordings show<br>that our approach yields more precise edge detection and image segmentation.<br>
Keypoint Message Passing for Video-Based Person Re-identification
D. Chen, A. Doering, S. Zhang, J. Yang, J. Gall and B. Schiele
Proceedings of the 36th AAAI Conference on Artificial Intelligence, 2022
D. Chen, A. Doering, S. Zhang, J. Yang, J. Gall and B. Schiele
Proceedings of the 36th AAAI Conference on Artificial Intelligence, 2022
PlanT: Explainable Planning Transformers via Object-Level Representations
K. Renz, K. Chitta, O.-B. Mercea, A. S. Koepke, Z. Akata and A. Geiger
Proceedings of the 6th Annual Conference on Robot Learning (CoRL 2022), 2022
K. Renz, K. Chitta, O.-B. Mercea, A. S. Koepke, Z. Akata and A. Geiger
Proceedings of the 6th Annual Conference on Robot Learning (CoRL 2022), 2022
Abstract
Planning an optimal route in a complex environment requires efficient<br>reasoning about the surrounding scene. While human drivers prioritize important<br>objects and ignore details not relevant to the decision, learning-based<br>planners typically extract features from dense, high-dimensional grid<br>representations containing all vehicle and road context information. In this<br>paper, we propose PlanT, a novel approach for planning in the context of<br>self-driving that uses a standard transformer architecture. PlanT is based on<br>imitation learning with a compact object-level input representation. On the<br>Longest6 benchmark for CARLA, PlanT outperforms all prior methods (matching the<br>driving score of the expert) while being 5.3x faster than equivalent<br>pixel-based planning baselines during inference. Combining PlanT with an<br>off-the-shelf perception module provides a sensor-based driving system that is<br>more than 10 points better in terms of driving score than the existing state of<br>the art. Furthermore, we propose an evaluation protocol to quantify the ability<br>of planners to identify relevant objects, providing insights regarding their<br>decision-making. Our results indicate that PlanT can focus on the most relevant<br>object in the scene, even when this object is geometrically distant.<br>
HRFuser: A Multi-resolution Sensor Fusion Architecture for 2D Object Detection
T. Broedermann, C. Sakaridis, D. Dai and L. Van Gool
Technical Report, 2022
(arXiv: 2206.15157) T. Broedermann, C. Sakaridis, D. Dai and L. Van Gool
Technical Report, 2022
Abstract
Besides standard cameras, autonomous vehicles typically include multiple<br>additional sensors, such as lidars and radars, which help acquire richer<br>information for perceiving the content of the driving scene. While several<br>recent works focus on fusing certain pairs of sensors - such as camera and<br>lidar or camera and radar - by using architectural components specific to the<br>examined setting, a generic and modular sensor fusion architecture is missing<br>from the literature. In this work, we focus on 2D object detection, a<br>fundamental high-level task which is defined on the 2D image domain, and<br>propose HRFuser, a multi-resolution sensor fusion architecture that scales<br>straightforwardly to an arbitrary number of input modalities. The design of<br>HRFuser is based on state-of-the-art high-resolution networks for image-only<br>dense prediction and incorporates a novel multi-window cross-attention block as<br>the means to perform fusion of multiple modalities at multiple resolutions.<br>Even though cameras alone provide very informative features for 2D detection,<br>we demonstrate via extensive experiments on the nuScenes and Seeing Through Fog<br>datasets that our model effectively leverages complementary features from<br>additional modalities, substantially improving upon camera-only performance and<br>consistently outperforming state-of-the-art fusion methods for 2D detection<br>both in normal and adverse conditions. The source code will be made publicly<br>available.<br>
An Embarrassingly Simple Baseline for Imbalanced Semi-Supervised Learning
H. Chen, Y. Fan, Y. Wang, J. Wang, B. Schiele, X. Xie, M. Savvides and B. Raj
Technical Report, 2022
(arXiv: 2211.11086) H. Chen, Y. Fan, Y. Wang, J. Wang, B. Schiele, X. Xie, M. Savvides and B. Raj
Technical Report, 2022
Abstract
Semi-supervised learning (SSL) has shown great promise in leveraging<br>unlabeled data to improve model performance. While standard SSL assumes uniform<br>data distribution, we consider a more realistic and challenging setting called<br>imbalanced SSL, where imbalanced class distributions occur in both labeled and<br>unlabeled data. Although there are existing endeavors to tackle this challenge,<br>their performance degenerates when facing severe imbalance since they can not<br>reduce the class imbalance sufficiently and effectively. In this paper, we<br>study a simple yet overlooked baseline -- SimiS -- which tackles data imbalance<br>by simply supplementing labeled data with pseudo-labels, according to the<br>difference in class distribution from the most frequent class. Such a simple<br>baseline turns out to be highly effective in reducing class imbalance. It<br>outperforms existing methods by a significant margin, e.g., 12.8%, 13.6%, and<br>16.7% over previous SOTA on CIFAR100-LT, FOOD101-LT, and ImageNet127<br>respectively. The reduced imbalance results in faster convergence and better<br>pseudo-label accuracy of SimiS. The simplicity of our method also makes it<br>possible to be combined with other re-balancing techniques to improve the<br>performance further. Moreover, our method shows great robustness to a wide<br>range of data distributions, which holds enormous potential in practice. Code<br>will be publicly available.<br>
Leveraging Self-Supervised Training for Unintentional Action Recognition
E. Duka, A. Kukleva and B. Schiele
Technical Report, 2022
(arXiv: 2209.11870) E. Duka, A. Kukleva and B. Schiele
Technical Report, 2022
Abstract
Unintentional actions are rare occurrences that are difficult to define<br>precisely and that are highly dependent on the temporal context of the action.<br>In this work, we explore such actions and seek to identify the points in videos<br>where the actions transition from intentional to unintentional. We propose a<br>multi-stage framework that exploits inherent biases such as motion speed,<br>motion direction, and order to recognize unintentional actions. To enhance<br>representations via self-supervised training for the task of unintentional<br>action recognition we propose temporal transformations, called Temporal<br>Transformations of Inherent Biases of Unintentional Actions (T2IBUA). The<br>multi-stage approach models the temporal information on both the level of<br>individual frames and full clips. These enhanced representations show strong<br>performance for unintentional action recognition tasks. We provide an extensive<br>ablation study of our framework and report results that significantly improve<br>over the state-of-the-art.<br>
Normalization Perturbation: A Simple Domain Generalization Method for Real-World Domain Shifts
Q. Fan, M. Segu, Y.-W. Tai, F. Yu, C.-K. Tang, B. Schiele and D. Dai
Technical Report, 2022
(arXiv: 2211.04393) Q. Fan, M. Segu, Y.-W. Tai, F. Yu, C.-K. Tang, B. Schiele and D. Dai
Technical Report, 2022
Abstract
Improving model's generalizability against domain shifts is crucial,<br>especially for safety-critical applications such as autonomous driving.<br>Real-world domain styles can vary substantially due to environment changes and<br>sensor noises, but deep models only know the training domain style. Such domain<br>style gap impedes model generalization on diverse real-world domains. Our<br>proposed Normalization Perturbation (NP) can effectively overcome this domain<br>style overfitting problem. We observe that this problem is mainly caused by the<br>biased distribution of low-level features learned in shallow CNN layers. Thus,<br>we propose to perturb the channel statistics of source domain features to<br>synthesize various latent styles, so that the trained deep model can perceive<br>diverse potential domains and generalizes well even without observations of<br>target domain data in training. We further explore the style-sensitive channels<br>for effective style synthesis. Normalization Perturbation only relies on a<br>single source domain and is surprisingly effective and extremely easy to<br>implement. Extensive experiments verify the effectiveness of our method for<br>generalizing models under real-world domain shifts.<br>
Visually Plausible Human-Object Interaction Capture from Wearable Sensors
V. Guzov, T. Sattler and G. Pons-Moll
Technical Report, 2022
(arXiv: 2205.02830) V. Guzov, T. Sattler and G. Pons-Moll
Technical Report, 2022
Abstract
In everyday lives, humans naturally modify the surrounding environment<br>through interactions, e.g., moving a chair to sit on it. To reproduce such<br>interactions in virtual spaces (e.g., metaverse), we need to be able to capture<br>and model them, including changes in the scene geometry, ideally from<br>ego-centric input alone (head camera and body-worn inertial sensors). This is<br>an extremely hard problem, especially since the object/scene might not be<br>visible from the head camera (e.g., a human not looking at a chair while<br>sitting down, or not looking at the door handle while opening a door). In this<br>paper, we present HOPS, the first method to capture interactions such as<br>dragging objects and opening doors from ego-centric data alone. Central to our<br>method is reasoning about human-object interactions, allowing to track objects<br>even when they are not visible from the head camera. HOPS localizes and<br>registers both the human and the dynamic object in a pre-scanned static scene.<br>HOPS is an important first step towards advanced AR/VR applications based on<br>immersive virtual universes, and can provide human-centric training data to<br>teach machines to interact with their surroundings. The supplementary video,<br>data, and code will be available on our project page at<br>http://virtualhumans.mpi-inf.mpg.de/hops/<br>
Lifted Edges as Connectivity Priors for Multicut and Disjoint Paths
A. Horňáková
PhD Thesis, Universität des Saarlandes, 2022
A. Horňáková
PhD Thesis, Universität des Saarlandes, 2022
Deep Gradient Learning for Efficient Camouflaged Object Detection
G.-P. Ji, D.-P. Fan, Y.-C. Chou, D. Dai, A. Liniger and L. Van Gool
Technical Report, 2022
(arXiv: 2205.12853) G.-P. Ji, D.-P. Fan, Y.-C. Chou, D. Dai, A. Liniger and L. Van Gool
Technical Report, 2022
Abstract
This paper introduces DGNet, a novel deep framework that exploits object<br>gradient supervision for camouflaged object detection (COD). It decouples the<br>task into two connected branches, i.e., a context and a texture encoder. The<br>essential connection is the gradient-induced transition, representing a soft<br>grouping between context and texture features. Benefiting from the simple but<br>efficient framework, DGNet outperforms existing state-of-the-art COD models by<br>a large margin. Notably, our efficient version, DGNet-S, runs in real-time (80<br>fps) and achieves comparable results to the cutting-edge model<br>JCSOD-CVPR$_{21}$ with only 6.82% parameters. Application results also show<br>that the proposed DGNet performs well in polyp segmentation, defect detection,<br>and transparent object segmentation tasks. Codes will be made available at<br>https://github.com/GewelsJI/DGNet.<br>
Control-NeRF: Editable Feature Volumes for Scene Rendering and Manipulation
V. Lazova, V. Guzov, K. Olszewski, S. Tulyakov and G. Pons-Moll
Technical Report, 2022
(arXiv: 2204.10850) V. Lazova, V. Guzov, K. Olszewski, S. Tulyakov and G. Pons-Moll
Technical Report, 2022
Abstract
We present a novel method for performing flexible, 3D-aware image content<br>manipulation while enabling high-quality novel view synthesis. While NeRF-based<br>approaches are effective for novel view synthesis, such models memorize the<br>radiance for every point in a scene within a neural network. Since these models<br>are scene-specific and lack a 3D scene representation, classical editing such<br>as shape manipulation, or combining scenes is not possible. Hence, editing and<br>combining NeRF-based scenes has not been demonstrated. With the aim of<br>obtaining interpretable and controllable scene representations, our model<br>couples learnt scene-specific feature volumes with a scene agnostic neural<br>rendering network. With this hybrid representation, we decouple neural<br>rendering from scene-specific geometry and appearance. We can generalize to<br>novel scenes by optimizing only the scene-specific 3D feature representation,<br>while keeping the parameters of the rendering network fixed. The rendering<br>function learnt during the initial training stage can thus be easily applied to<br>new scenes, making our approach more flexible. More importantly, since the<br>feature volumes are independent of the rendering model, we can manipulate and<br>combine scenes by editing their corresponding feature volumes. The edited<br>volume can then be plugged into the rendering model to synthesize high-quality<br>novel views. We demonstrate various scene manipulations, including mixing<br>scenes, deforming objects and inserting objects into scenes, while still<br>producing photo-realistic results.<br>
Discovering Class-Specific GAN Controls for Semantic Image Synthesis
E. Schönfeld, J. Borges, V. Sushko, B. Schiele and A. Khoreva
Technical Report, 2022
(arXiv: 2212.01455) E. Schönfeld, J. Borges, V. Sushko, B. Schiele and A. Khoreva
Technical Report, 2022
Abstract
Prior work has extensively studied the latent space structure of GANs for<br>unconditional image synthesis, enabling global editing of generated images by<br>the unsupervised discovery of interpretable latent directions. However, the<br>discovery of latent directions for conditional GANs for semantic image<br>synthesis (SIS) has remained unexplored. In this work, we specifically focus on<br>addressing this gap. We propose a novel optimization method for finding<br>spatially disentangled class-specific directions in the latent space of<br>pretrained SIS models. We show that the latent directions found by our method<br>can effectively control the local appearance of semantic classes, e.g.,<br>changing their internal structure, texture or color independently from each<br>other. Visual inspection and quantitative evaluation of the discovered GAN<br>controls on various datasets demonstrate that our method discovers a diverse<br>set of unique and semantically meaningful latent directions for class-specific<br>edits.<br>
MTR-A: 1st Place Solution for 2022 Waymo Open Dataset Challenge -- Motion Prediction
S. Shi, L. Jiang, D. Dai and B. Schiele
Technical Report, 2022
(arXiv: 2209.10033) S. Shi, L. Jiang, D. Dai and B. Schiele
Technical Report, 2022
Abstract
In this report, we present the 1st place solution for motion prediction track<br>in 2022 Waymo Open Dataset Challenges. We propose a novel Motion Transformer<br>framework for multimodal motion prediction, which introduces a small set of<br>novel motion query pairs for generating better multimodal future trajectories<br>by jointly performing the intention localization and iterative motion<br>refinement. A simple model ensemble strategy with non-maximum-suppression is<br>adopted to further boost the final performance. Our approach achieves the 1st<br>place on the motion prediction leaderboard of 2022 Waymo Open Dataset<br>Challenges, outperforming other methods with remarkable margins. Code will be<br>available at https://github.com/sshaoshuai/MTR.<br>
Understanding and Improving Robustness and Uncertainty Estimation in Deep Learning
D. Stutz
PhD Thesis, Universität des Saarlandes, 2022
D. Stutz
PhD Thesis, Universität des Saarlandes, 2022
Abstract
Deep learning is becoming increasingly relevant for many high-stakes applications such as autonomous driving or medical diagnosis where wrong decisions can have massive impact on human lives. Unfortunately, deep neural networks are typically assessed solely based on generalization, e.g., accuracy on a fixed test set. However, this is clearly insufficient for safe deployment as potential malicious actors and distribution shifts or the effects of quantization and unreliable hardware are disregarded. Thus, recent work additionally evaluates performance on potentially manipulated or corrupted inputs as well as after quantization and deployment on specialized hardware. In such settings, it is also important to obtain reasonable estimates of the model's confidence alongside its predictions. This thesis studies robustness and uncertainty estimation in deep learning along three main directions: First, we consider so-called adversarial examples, slightly perturbed inputs causing severe drops in accuracy. Second, we study weight perturbations, focusing particularly on bit errors in quantized weights. This is relevant for deploying models on special-purpose hardware for efficient inference, so-called accelerators. Finally, we address uncertainty estimation to improve robustness and provide meaningful statistical performance guarantees for safe deployment. In detail, we study the existence of adversarial examples with respect to the underlying data manifold. In this context, we also investigate adversarial training which improves robustness by augmenting training with adversarial examples at the cost of reduced accuracy. We show that regular adversarial examples leave the data manifold in an almost orthogonal direction. While we find no inherent trade-off between robustness and accuracy, this contributes to a higher sample complexity as well as severe overfitting of adversarial training. Using a novel measure of flatness in the robust loss landscape with respect to weight changes, we also show that robust overfitting is caused by converging to particularly sharp minima. In fact, we find a clear correlation between flatness and good robust generalization. Further, we study random and adversarial bit errors in quantized weights. In accelerators, random bit errors occur in the memory when reducing voltage with the goal of improving energy-efficiency. Here, we consider a robust quantization scheme, use weight clipping as regularization and perform random bit error training to improve bit error robustness, allowing considerable energy savings without requiring hardware changes. In contrast, adversarial bit errors are maliciously introduced through hardware- or software-based attacks on the memory, with severe consequences on performance. We propose a novel adversarial bit error attack to study this threat and use adversarial bit error training to improve robustness and thereby also the accelerator's security. Finally, we view robustness in the context of uncertainty estimation. By encouraging low-confidence predictions on adversarial examples, our confidence-calibrated adversarial training successfully rejects adversarial, corrupted as well as out-of-distribution examples at test time. Thereby, we are also able to improve the robustness-accuracy trade-off compared to regular adversarial training. However, even robust models do not provide any guarantee for safe deployment. To address this problem, conformal prediction allows the model to predict confidence sets with user-specified guarantee of including the true label. Unfortunately, as conformal prediction is usually applied after training, the model is trained without taking this calibration step into account. To address this limitation, we propose conformal training which allows training conformal predictors end-to-end with the underlying model. This not only improves the obtained uncertainty estimates but also enables optimizing application-specific objectives without losing the provided guarantee. Besides our work on robustness or uncertainty, we also address the problem of 3D shape completion of partially observed point clouds. Specifically, we consider an autonomous driving or robotics setting where vehicles are commonly equipped with LiDAR or depth sensors and obtaining a complete 3D representation of the environment is crucial. However, ground truth shapes that are essential for applying deep learning techniques are extremely difficult to obtain. Thus, we propose a weakly-supervised approach that can be trained on the incomplete point clouds while offering efficient inference. In summary, this thesis contributes to our understanding of robustness against both input and weight perturbations. To this end, we also develop methods to improve robustness alongside uncertainty estimation for safe deployment of deep learning methods in high-stakes applications. In the particular context of autonomous driving, we also address 3D shape completion of sparse point clouds.
Structured Prediction Problem Archive
P. Swoboda, A. Horňáková, P. Rötzer, B. Savchynskyy and A. Abbas
Technical Report, 2022
(arXiv: 2202.03574) P. Swoboda, A. Horňáková, P. Rötzer, B. Savchynskyy and A. Abbas
Technical Report, 2022
Abstract
Structured prediction problems are one of the fundamental tools in machine<br>learning. In order to facilitate algorithm development for their numerical<br>solution, we collect in one place a large number of datasets in easy to read<br>formats for a diverse set of problem classes. We provide archival links to<br>datasets, description of the considered problems and problem formats, and a<br>short summary of problem characteristics including size, number of instances<br>etc. For reference we also give a non-exhaustive selection of algorithms<br>proposed in the literature for their solution. We hope that this central<br>repository will make benchmarking and comparison to established works easier.<br>We welcome submission of interesting new datasets and algorithms for inclusion<br>in our archive.<br>
On Fragile Features and Batch Normalization in Adversarial Training
N. P. Walter, D. Stutz and B. Schiele
Technical Report, 2022
(arXiv: 2204.12393) N. P. Walter, D. Stutz and B. Schiele
Technical Report, 2022
Abstract
Modern deep learning architecture utilize batch normalization (BN) to<br>stabilize training and improve accuracy. It has been shown that the BN layers<br>alone are surprisingly expressive. In the context of robustness against<br>adversarial examples, however, BN is argued to increase vulnerability. That is,<br>BN helps to learn fragile features. Nevertheless, BN is still used in<br>adversarial training, which is the de-facto standard to learn robust features.<br>In order to shed light on the role of BN in adversarial training, we<br>investigate to what extent the expressiveness of BN can be used to robustify<br>fragile features in comparison to random features. On CIFAR10, we find that<br>adversarially fine-tuning just the BN layers can result in non-trivial<br>adversarial robustness. Adversarially training only the BN layers from scratch,<br>in contrast, is not able to convey meaningful adversarial robustness. Our<br>results indicate that fragile features can be used to learn models with<br>moderate adversarial robustness, while random features cannot<br>
Ret3D: Rethinking Object Relations for Efficient 3D Object Detection in Driving Scenes
Y.-H. Wu, D. Zhang, L. Zhang, X. Zhan, D. Dai, Y. Liu and M.-M. Cheng
Technical Report, 2022
(arXiv: 2208.08621) Y.-H. Wu, D. Zhang, L. Zhang, X. Zhan, D. Dai, Y. Liu and M.-M. Cheng
Technical Report, 2022
Abstract
Current efficient LiDAR-based detection frameworks are lacking in exploiting<br>object relations, which naturally present in both spatial and temporal manners.<br>To this end, we introduce a simple, efficient, and effective two-stage<br>detector, termed as Ret3D. At the core of Ret3D is the utilization of novel<br>intra-frame and inter-frame relation modules to capture the spatial and<br>temporal relations accordingly. More Specifically, intra-frame relation module<br>(IntraRM) encapsulates the intra-frame objects into a sparse graph and thus<br>allows us to refine the object features through efficient message passing. On<br>the other hand, inter-frame relation module (InterRM) densely connects each<br>object in its corresponding tracked sequences dynamically, and leverages such<br>temporal information to further enhance its representations efficiently through<br>a lightweight transformer network. We instantiate our novel designs of IntraRM<br>and InterRM with general center-based or anchor-based detectors and evaluate<br>them on Waymo Open Dataset (WOD). With negligible extra overhead, Ret3D<br>achieves the state-of-the-art performance, being 5.5% and 3.2% higher than the<br>recent competitor in terms of the LEVEL 1 and LEVEL 2 mAPH metrics on vehicle<br>detection, respectively.<br>
TOCH: Spatio-Temporal Object Correspondence to Hand for Motion Refinement
K. Zhou, B. Lal Bhatnagar, J. E. Lenssen and G. Pons-Moll
Technical Report, 2022
(arXiv: 2205.07982) K. Zhou, B. Lal Bhatnagar, J. E. Lenssen and G. Pons-Moll
Technical Report, 2022
Abstract
We present TOCH, a method for refining incorrect 3D hand-object interaction<br>sequences using a data prior. Existing hand trackers, especially those that<br>rely on very few cameras, often produce visually unrealistic results with<br>hand-object intersection or missing contacts. Although correcting such errors<br>requires reasoning about temporal aspects of interaction, most previous work<br>focus on static grasps and contacts. The core of our method are TOCH fields, a<br>novel spatio-temporal representation for modeling correspondences between hands<br>and objects during interaction. The key component is a point-wise<br>object-centric representation which encodes the hand position relative to the<br>object. Leveraging this novel representation, we learn a latent manifold of<br>plausible TOCH fields with a temporal denoising auto-encoder. Experiments<br>demonstrate that TOCH outperforms state-of-the-art (SOTA) 3D hand-object<br>interaction models, which are limited to static grasps and contacts. More<br>importantly, our method produces smooth interactions even before and after<br>contact. Using a single trained TOCH model, we quantitatively and qualitatively<br>demonstrate its usefulness for 1) correcting erroneous reconstruction results<br>from off-the-shelf RGB/RGB-D hand-object reconstruction methods, 2) de-noising,<br>and 3) grasp transfer across objects. We will release our code and trained<br>model on our project page at http://virtualhumans.mpi-inf.mpg.de/toch/<br>
Hypergraph Transformer for Skeleton-based Action Recognition
Y. Zhou, C. Li, Z.-Q. Cheng, Y. Geng, X. Xie and M. Keuper
Technical Report, 2022
(arXiv: 2211.09590) Y. Zhou, C. Li, Z.-Q. Cheng, Y. Geng, X. Xie and M. Keuper
Technical Report, 2022
Abstract
Skeleton-based action recognition aims to predict human actions given human<br>joint coordinates with skeletal interconnections. To model such off-grid data<br>points and their co-occurrences, Transformer-based formulations would be a<br>natural choice. However, Transformers still lag behind state-of-the-art methods<br>using graph convolutional networks (GCNs). Transformers assume that the input<br>is permutation-invariant and homogeneous (partially alleviated by positional<br>encoding), which ignores an important characteristic of skeleton data, i.e.,<br>bone connectivity. Furthermore, each type of body joint has a clear physical<br>meaning in human motion, i.e., motion retains an intrinsic relationship<br>regardless of the joint coordinates, which is not explored in Transformers. In<br>fact, certain re-occurring groups of body joints are often involved in specific<br>actions, such as the subconscious hand movement for keeping balance. Vanilla<br>attention is incapable of describing such underlying relations that are<br>persistent and beyond pair-wise. In this work, we aim to exploit these unique<br>aspects of skeleton data to close the performance gap between Transformers and<br>GCNs. Specifically, we propose a new self-attention (SA) extension, named<br>Hypergraph Self-Attention (HyperSA), to incorporate inherently higher-order<br>relations into the model. The K-hop relative positional embeddings are also<br>employed to take bone connectivity into account. We name the resulting model<br>Hyperformer, and it achieves comparable or better performance w.r.t. accuracy<br>and efficiency than state-of-the-art GCN architectures on NTU RGB+D, NTU RGB+D<br>120, and Northwestern-UCLA datasets. On the largest NTU RGB+D 120 dataset, the<br>significantly improved performance reached by our Hyperformer demonstrates the<br>underestimated potential of Transformer models in this field.<br>
2021
Real-time Deep Dynamic Characters
M. Habermann, L. Liu, W. Xu, M. Zollhöfer, G. Pons-Moll and C. Theobalt
ACM Transactions on Graphics (Proc. ACM SIGGRAPH 2021), Volume 40, Number 4, 2021
M. Habermann, L. Liu, W. Xu, M. Zollhöfer, G. Pons-Moll and C. Theobalt
ACM Transactions on Graphics (Proc. ACM SIGGRAPH 2021), Volume 40, Number 4, 2021
Fine-Grained Zero-Shot Learning with DNA as Side Information
S. Badirli, Z. Akata, G. Mohler, C. Picard and M. M. Dundar
Advances in Neural Information Processing Systems 34 (NeurIPS 2021), 2021
S. Badirli, Z. Akata, G. Mohler, C. Picard and M. M. Dundar
Advances in Neural Information Processing Systems 34 (NeurIPS 2021), 2021
RMM: Reinforced Memory Management for Class-Incremental Learning
Y. Liu, B. Schiele and Q. Sun
Advances in Neural Information Processing Systems 34 (NeurIPS 2021), 2021
Y. Liu, B. Schiele and Q. Sun
Advances in Neural Information Processing Systems 34 (NeurIPS 2021), 2021
Shape your Space: A Gaussian Mixture Regularization Approach to Deterministic Autoencoders
A. Saseendran, K. Skubch, S. Falkner and M. Keuper
Advances in Neural Information Processing Systems 34 Pre-Proceedings (NeurIPS 2021), 2021
A. Saseendran, K. Skubch, S. Falkner and M. Keuper
Advances in Neural Information Processing Systems 34 Pre-Proceedings (NeurIPS 2021), 2021
mDALU: Multi-Source Domain Adaptation and Label Unification with Partial Datasets
R. Gong, D. Dai, Y. Chen, W. Li and L. Van Gool
ICCV 2021, IEEE/CVF International Conference on Computer Vision, 2021
R. Gong, D. Dai, Y. Chen, W. Li and L. Van Gool
ICCV 2021, IEEE/CVF International Conference on Computer Vision, 2021
Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weather
M. Hahner, C. Sakaridis, D. Dai and L. Van Gool
ICCV 2021, IEEE/CVF International Conference on Computer Vision, 2021
M. Hahner, C. Sakaridis, D. Dai and L. Van Gool
ICCV 2021, IEEE/CVF International Conference on Computer Vision, 2021
Making Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint Paths
A. Horňáková, T. Kaiser, P. Swoboda, M. Rolinek, B. Rosenhahn and R. Henschel
ICCV 2021, IEEE/CVF International Conference on Computer Vision, 2021
A. Horňáková, T. Kaiser, P. Swoboda, M. Rolinek, B. Rosenhahn and R. Henschel
ICCV 2021, IEEE/CVF International Conference on Computer Vision, 2021
e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks
M. Kayser, O.-M. Camburu, L. Salewski, C. Emde, V. Do, Z. Akata and T. Lukasiewicz
ICCV 2021, IEEE/CVF International Conference on Computer Vision, 2021
M. Kayser, O.-M. Camburu, L. Salewski, C. Emde, V. Do, Z. Akata and T. Lukasiewicz
ICCV 2021, IEEE/CVF International Conference on Computer Vision, 2021
Keep CALM and Improve Visual Feature Attribution
J. M. Kim, J. Choe, Z. Akata and S. J. Oh
ICCV 2021, IEEE/CVF International Conference on Computer Vision, 2021
J. M. Kim, J. Choe, Z. Akata and S. J. Oh
ICCV 2021, IEEE/CVF International Conference on Computer Vision, 2021
Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgetting
A. Kukleva, H. Kuehne and B. Schiele
ICCV 2021, IEEE/CVF International Conference on Computer Vision, 2021
A. Kukleva, H. Kuehne and B. Schiele
ICCV 2021, IEEE/CVF International Conference on Computer Vision, 2021
Seeking Similarities over Differences: Similarity-based Domain Alignment for Adaptive Object Detection
F. Rezaeianaran, R. Shetty, R. Aljundi, D. O. Reino, S. Zhang and B. Schiele
ICCV 2021, IEEE/CVF International Conference on Computer Vision, 2021
F. Rezaeianaran, R. Shetty, R. Aljundi, D. O. Reino, S. Zhang and B. Schiele
ICCV 2021, IEEE/CVF International Conference on Computer Vision, 2021
ACDC: The Adverse Conditions Dataset with Correspondences for Semantic Driving Scene Understanding
C. Sakaridis, D. Dai and L. Van Gool
ICCV 2021, IEEE/CVF International Conference on Computer Vision, 2021
C. Sakaridis, D. Dai and L. Van Gool
ICCV 2021, IEEE/CVF International Conference on Computer Vision, 2021
Relating Adversarially Robust Generalization to Flat Minima
D. Stutz, M. Hein and B. Schiele
ICCV 2021, IEEE/CVF International Conference on Computer Vision, 2021
D. Stutz, M. Hein and B. Schiele
ICCV 2021, IEEE/CVF International Conference on Computer Vision, 2021
Task Switching Network for Multi-task Learning
G. Sun, T. Probst, D. P. Paudel, N. Popovic, M. Kanakis, J. Patel, D. Dai and L. Van Gool
ICCV 2021, IEEE/CVF International Conference on Computer Vision, 2021
G. Sun, T. Probst, D. P. Paudel, N. Popovic, M. Kanakis, J. Patel, D. Dai and L. Van Gool
ICCV 2021, IEEE/CVF International Conference on Computer Vision, 2021
Neural-GIF: Neural Generalized Implicit Functions for Animating People in Clothing
G. Tiwari, N. Sarafianos, T. Tung and G. Pons-Moll
ICCV 2021, IEEE/CVF International Conference on Computer Vision, 2021
G. Tiwari, N. Sarafianos, T. Tung and G. Pons-Moll
ICCV 2021, IEEE/CVF International Conference on Computer Vision, 2021
Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimation
Q. Wang, D. Dai, L. Hoyer, L. Van Gool and O. Fink
ICCV 2021, IEEE/CVF International Conference on Computer Vision, 2021
Q. Wang, D. Dai, L. Hoyer, L. Van Gool and O. Fink
ICCV 2021, IEEE/CVF International Conference on Computer Vision, 2021
Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data
N. Yu, V. Skripniuk, S. Abdelnabi and M. Fritz
ICCV 2021, IEEE/CVF International Conference on Computer Vision, 2021
N. Yu, V. Skripniuk, S. Abdelnabi and M. Fritz
ICCV 2021, IEEE/CVF International Conference on Computer Vision, 2021
Dual Contrastive Loss and Attention for GANs
N. Yu, G. Liu, A. Dundar, A. Tao, B. Catanzaro, L. Davis and M. Fritz
ICCV 2021, IEEE/CVF International Conference on Computer Vision, 2021
N. Yu, G. Liu, A. Dundar, A. Tao, B. Catanzaro, L. Davis and M. Fritz
ICCV 2021, IEEE/CVF International Conference on Computer Vision, 2021
End-to-End Urban Driving by Imitating a Reinforcement Learning Coach
Z. Zhang, A. Liniger, D. Dai, F. Yu and L. Van Gool
ICCV 2021, IEEE/CVF International Conference on Computer Vision, 2021
Z. Zhang, A. Liniger, D. Dai, F. Yu and L. Van Gool
ICCV 2021, IEEE/CVF International Conference on Computer Vision, 2021
Learning Decision Trees Recurrently Through Communication
S. Alaniz, D. Marcos, B. Schiele and Z. Akata
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021), 2021
S. Alaniz, D. Marcos, B. Schiele and Z. Akata
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021), 2021
Euro-PVI: Pedestrian Vehicle Interactions in Dense Urban Centers
A. Bhattacharyya, D. O. Reino, M. Fritz and B. Schiele
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021), 2021
A. Bhattacharyya, D. O. Reino, M. Fritz and B. Schiele
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021), 2021
Convolutional Dynamic Alignment Networks for Interpretable Classifications
M. D. Böhle, M. Fritz and B. Schiele
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021), 2021
M. D. Böhle, M. Fritz and B. Schiele
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021), 2021
Distilling Audio-Visual Knowledge by Compositional Contrastive Learning
Y. Chen, Y. Xian, A. S. Koepke and Z. Akata
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021), 2021
Y. Chen, Y. Xian, A. S. Koepke and Z. Akata
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021), 2021
Stereo Radiance Fields (SRF): Learning View Synthesis from Sparse Views of Novel Scenes
J. Chibane, A. Bansal, V. Lazova and G. Pons-Moll
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021), 2021
J. Chibane, A. Bansal, V. Lazova and G. Pons-Moll
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021), 2021
Learning Spatially-Variant MAP Models for Non-blind Image Deblurring
J. Dong, S. Roth and B. Schiele
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021), 2021
J. Dong, S. Roth and B. Schiele
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021), 2021
Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensors
V. Guzov, A. Mir, T. Sattler, and G. Pons-Moll
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021), 2021
V. Guzov, A. Mir, T. Sattler, and G. Pons-Moll
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021), 2021
Adaptive Aggregation Networks for Class-Incremental Learning
Y. Liu, B. Schiele and Q. Sun
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021), 2021
Y. Liu, B. Schiele and Q. Sun
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021), 2021
Open World Compositional Zero-Shot Learning
M. Mancini, M. F. Naeem, Y. Xian and Z. Akata
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021), 2021
M. Mancini, M. F. Naeem, Y. Xian and Z. Akata
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021), 2021
Learning Graph Embeddings for Compositional Zero-shot Learning
M. F. Naeem, Y. Xian, F. Tombari and Z. Akata
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021), 2021
M. F. Naeem, Y. Xian, F. Tombari and Z. Akata
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021), 2021
D-NeRF: Neural Radiance Fields for Dynamic Scenes
A. Pumarola, E. Corona, G. Pons-Moll and F. Moreno-Noguer
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021), 2021
A. Pumarola, E. Corona, G. Pons-Moll and F. Moreno-Noguer
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021), 2021
Future Moment Assessment for Action Query
Q. Ke, M. Fritz and B. Schiele
IEEE Winter Conference on Applications of Computer Vision (WACV 2021), 2021
Q. Ke, M. Fritz and B. Schiele
IEEE Winter Conference on Applications of Computer Vision (WACV 2021), 2021
Joint Visual-Temporal Embedding for Unsupervised Learning of Actions in Untrimmed Sequences
R. G. VidalMata, W. J. Scheirer, A. Kukleva, D. Cox and H. Kuehne
IEEE Winter Conference on Applications of Computer Vision (WACV 2021), 2021
R. G. VidalMata, W. J. Scheirer, A. Kukleva, D. Cox and H. Kuehne
IEEE Winter Conference on Applications of Computer Vision (WACV 2021), 2021
You Only Need Adversarial Supervision for Semantic Image Synthesis
E. Schönfeld, V. Sushko, D. Zhang, J. Gall, B. Schiele and A. Khoreva
International Conference on Learning Representations (ICLR 2021), 2021
E. Schönfeld, V. Sushko, D. Zhang, J. Gall, B. Schiele and A. Khoreva
International Conference on Learning Representations (ICLR 2021), 2021
Semantic Bottlenecks: Quantifying and Improving Inspectability of Deep Representations
M. Losch, M. Fritz and B. Schiele
International Journal of Computer Vision, Volume 129, 2021
M. Losch, M. Fritz and B. Schiele
International Journal of Computer Vision, Volume 129, 2021
SampleFix: Learning to Correct Programs by Sampling Diverse Fixes
H. Hajipour, A. Bhattacharyya, C.-A. Staicu and M. Fritz
Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2021), 2021
H. Hajipour, A. Bhattacharyya, C.-A. Staicu and M. Fritz
Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2021), 2021
Internalized Biases in Fréchet Inception Distance
S. Jung and M. Keuper
NeurIPS 2021 Workshop on Distribution Shifts: Connecting Methods and Applications (NeurIPS 2021 Workshop DistShift), 2021
S. Jung and M. Keuper
NeurIPS 2021 Workshop on Distribution Shifts: Connecting Methods and Applications (NeurIPS 2021 Workshop DistShift), 2021
(SP)2Net for Generalized Zero-Label Semantic Segmentation
A. Das, Y. Xian, Y. He, B. Schiele and Z. Akata
Pattern Recognition (GCPR 2021), 2021
A. Das, Y. Xian, Y. He, B. Schiele and Z. Akata
Pattern Recognition (GCPR 2021), 2021
Efficient Message Passing for 0–1 ILPs with Binary Decision Diagrams
J.-H. Lange and P. Swoboda
Proceedings of the 38th International Conference on Machine Learning (ICML 2021), 2021
J.-H. Lange and P. Swoboda
Proceedings of the 38th International Conference on Machine Learning (ICML 2021), 2021
Bit Error Robustness for Energy-Efficient DNN Accelerators
D. Stutz, N. Chandramoorthy, M. Hein and B. Schiele
Proceedings of the 4th MLSys Conference, 2021
D. Stutz, N. Chandramoorthy, M. Hein and B. Schiele
Proceedings of the 4th MLSys Conference, 2021
Abstract
Deep neural network (DNN) accelerators received considerable attention in<br>past years due to saved energy compared to mainstream hardware. Low-voltage<br>operation of DNN accelerators allows to further reduce energy consumption<br>significantly, however, causes bit-level failures in the memory storing the<br>quantized DNN weights. In this paper, we show that a combination of robust<br>fixed-point quantization, weight clipping, and random bit error training<br>(RandBET) improves robustness against random bit errors in (quantized) DNN<br>weights significantly. This leads to high energy savings from both low-voltage<br>operation as well as low-precision quantization. Our approach generalizes<br>across operating voltages and accelerators, as demonstrated on bit errors from<br>profiled SRAM arrays. We also discuss why weight clipping alone is already a<br>quite effective way to achieve robustness against bit errors. Moreover, we<br>specifically discuss the involved trade-offs regarding accuracy, robustness and<br>precision: Without losing more than 1% in accuracy compared to a normally<br>trained 8-bit DNN, we can reduce energy consumption on CIFAR-10 by 20%. Higher<br>energy savings of, e.g., 30%, are possible at the cost of 2.5% accuracy, even<br>for 4-bit DNNs.<br>
A Closer Look at Self-training for Zero-Label Semantic Segmentation
G. Pastore, F. Cermelli, Y. Xian, M. Mancini, Z. Akata and B. Caputo
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPR 2021), 2021
G. Pastore, F. Cermelli, Y. Xian, M. Mancini, Z. Akata and B. Caputo
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPR 2021), 2021
InfoScrub: Towards Attribute Privacy by Targeted Obfuscation
H.-P. Wang, T. Orekondy and M. Fritz
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPR 2021), 2021
H.-P. Wang, T. Orekondy and M. Fritz
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPR 2021), 2021
Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis
Y. He, N. Yu, M. Keuper and M. Fritz
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (IJCAI 2021), 2021
Y. He, N. Yu, M. Keuper and M. Fritz
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (IJCAI 2021), 2021
FastDOG: Fast Discrete Optimization on GPU
A. Abbas and P. Swoboda
Technical Report, 2021
(arXiv: 2111.10270) A. Abbas and P. Swoboda
Technical Report, 2021
Abstract
We present a massively parallel Lagrange decomposition method for solving 0-1<br>integer linear programs occurring in structured prediction. We propose a new<br>iterative update scheme for solving the Lagrangean dual and a perturbation<br>technique for decoding primal solutions. For representing subproblems we follow<br>Lange et al. (2021) and use binary decision diagrams (BDDs). Our primal and<br>dual algorithms require little synchronization between subproblems and<br>optimization over BDDs needs only elementary operations without complicated<br>control flow. This allows us to exploit the parallelism offered by GPUs for all<br>components of our method. We present experimental results on combinatorial<br>problems from MAP inference for Markov Random Fields, quadratic assignment and<br>cell tracking for developmental biology. Our highly parallel GPU implementation<br>improves upon the running times of the algorithms from Lange et al. (2021) by<br>up to an order of magnitude. In particular, we come close to or outperform some<br>state-of-the-art specialized heuristics while being problem agnostic.<br>
Long-term future prediction under uncertainty and multi-modality
A. Bhattacharyya
PhD Thesis, Universität des Saarlandes, 2021
A. Bhattacharyya
PhD Thesis, Universität des Saarlandes, 2021
Where and When: Space-Time Attention for Audio-Visual Explanations
Y. Chen, T. Hummel, A. S. Koepke and Z. Akata
Technical Report, 2021
(arXiv: 2105.01517) Y. Chen, T. Hummel, A. S. Koepke and Z. Akata
Technical Report, 2021
Abstract
Explaining the decision of a multi-modal decision-maker requires to determine<br>the evidence from both modalities. Recent advances in XAI provide explanations<br>for models trained on still images. However, when it comes to modeling multiple<br>sensory modalities in a dynamic world, it remains underexplored how to<br>demystify the mysterious dynamics of a complex multi-modal model. In this work,<br>we take a crucial step forward and explore learnable explanations for<br>audio-visual recognition. Specifically, we propose a novel space-time attention<br>network that uncovers the synergistic dynamics of audio and visual data over<br>both space and time. Our model is capable of predicting the audio-visual video<br>events, while justifying its decision by localizing where the relevant visual<br>cues appear, and when the predicted sounds occur in videos. We benchmark our<br>model on three audio-visual video event datasets, comparing extensively to<br>multiple recent multi-modal representation learners and intrinsic explanation<br>models. Experimental results demonstrate the clear superior performance of our<br>model over the existing methods on audio-visual video event recognition.<br>Moreover, we conduct an in-depth study to analyze the explainability of our<br>model based on robustness analysis via perturbation tests and pointing games<br>using human annotations.<br>
TADA: Taxonomy Adaptive Domain Adaptation
R. Gong, M. Danelljan, D. Dai, W. Wang, D. P. Paudel, A. Chhatkuli, F. Yu and L. Van Gool
Technical Report, 2021
(arXiv: 2109.04813) R. Gong, M. Danelljan, D. Dai, W. Wang, D. P. Paudel, A. Chhatkuli, F. Yu and L. Van Gool
Technical Report, 2021
Abstract
Traditional domain adaptation addresses the task of adapting a model to a<br>novel target domain under limited or no additional supervision. While tackling<br>the input domain gap, the standard domain adaptation settings assume no domain<br>change in the output space. In semantic prediction tasks, different datasets<br>are often labeled according to different semantic taxonomies. In many<br>real-world settings, the target domain task requires a different taxonomy than<br>the one imposed by the source domain. We therefore introduce the more general<br>taxonomy adaptive domain adaptation (TADA) problem, allowing for inconsistent<br>taxonomies between the two domains. We further propose an approach that jointly<br>addresses the image-level and label-level domain adaptation. On the<br>label-level, we employ a bilateral mixed sampling strategy to augment the<br>target domain, and a relabelling method to unify and align the label spaces. We<br>address the image-level domain gap by proposing an uncertainty-rectified<br>contrastive learning method, leading to more domain-invariant and class<br>discriminative features. We extensively evaluate the effectiveness of our<br>framework under different TADA settings: open taxonomy, coarse-to-fine<br>taxonomy, and partially-overlapping taxonomy. Our framework outperforms<br>previous state-of-the-art by a large margin, while capable of adapting to<br>target taxonomies.<br>
Learning Graph Embeddings for Open World Compositional Zero-Shot Learning
M. Mancini, M. F. Naeem, Y. Xian and Z. Akata
Technical Report, 2021
(arXiv: 2105.01017) M. Mancini, M. F. Naeem, Y. Xian and Z. Akata
Technical Report, 2021
Abstract
Compositional Zero-Shot learning (CZSL) aims to recognize unseen compositions<br>of state and object visual primitives seen during training. A problem with<br>standard CZSL is the assumption of knowing which unseen compositions will be<br>available at test time. In this work, we overcome this assumption operating on<br>the open world setting, where no limit is imposed on the compositional space at<br>test time, and the search space contains a large number of unseen compositions.<br>To address this problem, we propose a new approach, Compositional Cosine Graph<br>Embeddings (Co-CGE), based on two principles. First, Co-CGE models the<br>dependency between states, objects and their compositions through a graph<br>convolutional neural network. The graph propagates information from seen to<br>unseen concepts, improving their representations. Second, since not all unseen<br>compositions are equally feasible, and less feasible ones may damage the<br>learned representations, Co-CGE estimates a feasibility score for each unseen<br>composition, using the scores as margins in a cosine similarity-based loss and<br>as weights in the adjacency matrix of the graphs. Experiments show that our<br>approach achieves state-of-the-art performances in standard CZSL while<br>outperforming previous methods in the open world scenario.<br>
From Pixels to People
M. Omran
PhD Thesis, Universität des Saarlandes, 2021
M. Omran
PhD Thesis, Universität des Saarlandes, 2021
Abstract
Abstract<br>Humans are at the centre of a significant amount of research in computer vision.<br>Endowing machines with the ability to perceive people from visual data is an immense<br>scientific challenge with a high degree of direct practical relevance. Success in automatic<br>perception can be measured at different levels of abstraction, and this will depend on<br>which intelligent behaviour we are trying to replicate: the ability to localise persons in<br>an image or in the environment, understanding how persons are moving at the skeleton<br>and at the surface level, interpreting their interactions with the environment including<br>with other people, and perhaps even anticipating future actions. In this thesis we tackle<br>different sub-problems of the broad research area referred to as "looking at people",<br>aiming to perceive humans in images at different levels of granularity.<br>We start with bounding box-level pedestrian detection: We present a retrospective<br>analysis of methods published in the decade preceding our work, identifying various<br>strands of research that have advanced the state of the art. With quantitative exper-<br>iments, we demonstrate the critical role of developing better feature representations<br>and having the right training distribution. We then contribute two methods based<br>on the insights derived from our analysis: one that combines the strongest aspects of<br>past detectors and another that focuses purely on learning representations. The latter<br>method outperforms more complicated approaches, especially those based on hand-<br>crafted features. We conclude our work on pedestrian detection with a forward-looking<br>analysis that maps out potential avenues for future research.<br>We then turn to pixel-level methods: Perceiving humans requires us to both separate<br>them precisely from the background and identify their surroundings. To this end, we<br>introduce Cityscapes, a large-scale dataset for street scene understanding. This has since<br>established itself as a go-to benchmark for segmentation and detection. We additionally<br>develop methods that relax the requirement for expensive pixel-level annotations, focusing<br>on the task of boundary detection, i.e. identifying the outlines of relevant objects and<br>surfaces. Next, we make the jump from pixels to 3D surfaces, from localising and<br>labelling to fine-grained spatial understanding. We contribute a method for recovering<br>3D human shape and pose, which marries the advantages of learning-based and model-<br>based approaches.<br>We conclude the thesis with a detailed discussion of benchmarking practices in<br>computer vision. Among other things, we argue that the design of future datasets<br>should be driven by the general goal of combinatorial robustness besides task-specific<br>considerations.
Adversarial Content Manipulation for Analyzing and Improving Model Robustness
R. Shetty
PhD Thesis, Universität des Saarlandes, 2021
R. Shetty
PhD Thesis, Universität des Saarlandes, 2021
Adjoint Rigid Transform Network: Task-conditioned Alignment of 3D Shapes
K. Zhou, B. L. Bhatnagar, B. Schiele and G. Pons-Moll
Technical Report, 2021
(arXiv: 2102.01161) K. Zhou, B. L. Bhatnagar, B. Schiele and G. Pons-Moll
Technical Report, 2021
Abstract
Most learning methods for 3D data (point clouds, meshes) suffer significant<br>performance drops when the data is not carefully aligned to a canonical<br>orientation. Aligning real world 3D data collected from different sources is<br>non-trivial and requires manual intervention. In this paper, we propose the<br>Adjoint Rigid Transform (ART) Network, a neural module which can be integrated<br>with a variety of 3D networks to significantly boost their performance. ART<br>learns to rotate input shapes to a learned canonical orientation, which is<br>crucial for a lot of tasks such as shape reconstruction, interpolation,<br>non-rigid registration, and latent disentanglement. ART achieves this with<br>self-supervision and a rotation equivariance constraint on predicted rotations.<br>The remarkable result is that with only self-supervision, ART facilitates<br>learning a unique canonical orientation for both rigid and nonrigid shapes,<br>which leads to a notable boost in performance of aforementioned tasks. We will<br>release our code and pre-trained models for further research.<br>
2020
XNect: Real-time Multi-person 3D Human Pose Estimation with a Single RGB Camera
D. Mehta, O. Sotnychenko, F. Mueller, W. Xu, M. Elgharib, P. Fua, H.-P. Seidel, H. Rhodin, G. Pons-Moll and C. Theobalt
ACM Transactions on Graphics (Proc. ACM SIGGRAPH 2020), Volume 39, Number 4, 2020
D. Mehta, O. Sotnychenko, F. Mueller, W. Xu, M. Elgharib, P. Fua, H.-P. Seidel, H. Rhodin, G. Pons-Moll and C. Theobalt
ACM Transactions on Graphics (Proc. ACM SIGGRAPH 2020), Volume 39, Number 4, 2020
LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registration
B. L. Bhatnagar, C. Sminchisescu, C. Theobalt and G. Pons-Moll
Advances in Neural Information Processing Systems 33 (NeurIPS 2020), 2020
B. L. Bhatnagar, C. Sminchisescu, C. Theobalt and G. Pons-Moll
Advances in Neural Information Processing Systems 33 (NeurIPS 2020), 2020
Neural Unsigned Distance Fields for Implicit Function Learning
J. Chibane, A. Mir and G. Pons-Moll
Advances in Neural Information Processing Systems 33 (NeurIPS 2020), 2020
J. Chibane, A. Mir and G. Pons-Moll
Advances in Neural Information Processing Systems 33 (NeurIPS 2020), 2020
Deep Wiener Deconvolution: Wiener Meets Deep Learning for Image Deblurring
J. Dong, S. Roth and B. Schiele
Advances in Neural Information Processing Systems 33 (NeurIPS 2020), 2020
J. Dong, S. Roth and B. Schiele
Advances in Neural Information Processing Systems 33 (NeurIPS 2020), 2020
Attribute Prototype Network for Zero-Shot Learning
W. Xu, Y. Xian, J. Wang, B. Schiele and Z. Akata
Advances in Neural Information Processing Systems 33 (NeurIPS 2020), 2020
W. Xu, Y. Xian, J. Wang, B. Schiele and Z. Akata
Advances in Neural Information Processing Systems 33 (NeurIPS 2020), 2020
Body Shape Privacy in Images: Understanding Privacy and Preventing Automatic Shape Extraction
H. Sattar, K. Krombholz, G. Pons-Moll and M. Fritz
Computer Vision -- ECCV Workshops 2020, 2020
H. Sattar, K. Krombholz, G. Pons-Moll and M. Fritz
Computer Vision -- ECCV Workshops 2020, 2020
Abstract
Modern approaches to pose and body shape estimation have recently achieved<br>strong performance even under challenging real-world conditions. Even from a<br>single image of a clothed person, a realistic looking body shape can be<br>inferred that captures a users' weight group and body shape type well. This<br>opens up a whole spectrum of applications -- in particular in fashion -- where<br>virtual try-on and recommendation systems can make use of these new and<br>automatized cues. However, a realistic depiction of the undressed body is<br>regarded highly private and therefore might not be consented by most people.<br>Hence, we ask if the automatic extraction of such information can be<br>effectively evaded. While adversarial perturbations have been shown to be<br>effective for manipulating the output of machine learning models -- in<br>particular, end-to-end deep learning approaches -- state of the art shape<br>estimation methods are composed of multiple stages. We perform the first<br>investigation of different strategies that can be used to effectively<br>manipulate the automatic shape estimation while preserving the overall<br>appearance of the original image.<br>
DeepCap: Monocular Human Performance Capture Using Weak Supervision
M. Habermann, W. Xu, M. Zollhöfer, G. Pons-Moll and C. Theobalt
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020), 2020
M. Habermann, W. Xu, M. Zollhöfer, G. Pons-Moll and C. Theobalt
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020), 2020
SelfPose: 3D Egocentric Pose Estimation from a Headset Mounted Camera
D. Tome, T. Alldieck, P. Peluse, G. Pons-Moll, L. Agapito, H. Badino and F. de la Torre
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020
D. Tome, T. Alldieck, P. Peluse, G. Pons-Moll, L. Agapito, H. Badino and F. de la Torre
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020
Learning Robust Representations via Multi-View Information Bottleneck
M. Federici, A. Dutta, P. Forré, N. Kushman and Z. Akata
International Conference on Learning Representations (ICLR 2020), 2020
M. Federici, A. Dutta, P. Forré, N. Kushman and Z. Akata
International Conference on Learning Representations (ICLR 2020), 2020
Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attacks
T. Orekondy, B. Schiele and M. Fritz
International Conference on Learning Representations (ICLR 2020), 2020
T. Orekondy, B. Schiele and M. Fritz
International Conference on Learning Representations (ICLR 2020), 2020
Semantically Tied Paired Cycle Consistency for Any-Shot Sketch-based Image Retrieval
A. Dutta and Z. Akata
International Journal of Computer Vision, Volume 128, 2020
A. Dutta and Z. Akata
International Journal of Computer Vision, Volume 128, 2020
Diverse and Relevant Visual Storytelling with Scene Graph Embeddings
X. Hong, R. Shetty, A. Sayeed, K. Mehra, V. Demberg and B. Schiele
Proceedings of the 24th Conference on Computational Natural Language Learning (CoNLL 2020), 2020
X. Hong, R. Shetty, A. Sayeed, K. Mehra, V. Demberg and B. Schiele
Proceedings of the 24th Conference on Computational Natural Language Learning (CoNLL 2020), 2020
Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learning
A. M. G. Salem, A. Bhattacharyya, M. Backes, M. Fritz and Y. Zhang
Proceedings of the 29th USENIX Security Symposium, 2020
A. M. G. Salem, A. Bhattacharyya, M. Backes, M. Fritz and Y. Zhang
Proceedings of the 29th USENIX Security Symposium, 2020
Lifted Disjoint Paths with Application in Multiple Object Tracking
A. Horňáková, R. Henschel, B. Rosenhahn and P. Swoboda
Proceedings of the 37th International Conference on Machine Learning (ICML 2020), 2020
A. Horňáková, R. Henschel, B. Rosenhahn and P. Swoboda
Proceedings of the 37th International Conference on Machine Learning (ICML 2020), 2020
Confidence-Calibrated Adversarial Training: Generalizing to Unseen Attacks
D. Stutz, M. Hein and B. Schiele
Proceedings of the 37th International Conference on Machine Learning (ICML 2020), 2020
D. Stutz, M. Hein and B. Schiele
Proceedings of the 37th International Conference on Machine Learning (ICML 2020), 2020
A Primal-Dual Solver for Large-Scale Tracking-by-Assignment
S. Haller, M. Prakash, L. Hutschenreiter, T. Pietzsch, C. Rother, F. Jug, P. Swoboda and B. Savchynskyy
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics (AISTATS 2020), 2020
S. Haller, M. Prakash, L. Hutschenreiter, T. Pietzsch, C. Rother, F. Jug, P. Swoboda and B. Savchynskyy
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics (AISTATS 2020), 2020
CLEVR-X: A Visual Reasoning Dataset for Natural Language Explanations
L. Salewski, A. S. Koepke, H. P. A. Lensch and Z. Akata
xxAI -- Beyond Explainable AI (xxAI @ICML 2020), 2020
L. Salewski, A. S. Koepke, H. P. A. Lensch and Z. Akata
xxAI -- Beyond Explainable AI (xxAI @ICML 2020), 2020
PoseTrackReID: Dataset Description
A. Doering, D. Chen, S. Zhang, B. Schiele and J. Gall
Technical Report, 2020
(arXiv: 2011.06243) A. Doering, D. Chen, S. Zhang, B. Schiele and J. Gall
Technical Report, 2020
Abstract
Current datasets for video-based person re-identification (re-ID) do not<br>include structural knowledge in form of human pose annotations for the persons<br>of interest. Nonetheless, pose information is very helpful to disentangle<br>useful feature information from background or occlusion noise. Especially<br>real-world scenarios, such as surveillance, contain a lot of occlusions in<br>human crowds or by obstacles. On the other hand, video-based person re-ID can<br>benefit other tasks such as multi-person pose tracking in terms of robust<br>feature matching. For that reason, we present PoseTrackReID, a large-scale<br>dataset for multi-person pose tracking and video-based person re-ID. With<br>PoseTrackReID, we want to bridge the gap between person re-ID and multi-person<br>pose tracking. Additionally, this dataset provides a good benchmark for current<br>state-of-the-art methods on multi-frame person re-ID.<br>
Analyzing the Dependency of ConvNets on Spatial Information
Y. Fan, Y. Xian, M. M. Losch and B. Schiele
Technical Report, 2020
(arXiv: 2002.01827) Y. Fan, Y. Xian, M. M. Losch and B. Schiele
Technical Report, 2020
Abstract
Intuitively, image classification should profit from using spatial<br>information. Recent work, however, suggests that this might be overrated in<br>standard CNNs. In this paper, we are pushing the envelope and aim to further<br>investigate the reliance on spatial information. We propose spatial shuffling<br>and GAP+FC to destroy spatial information during both training and testing<br>phases. Interestingly, we observe that spatial information can be deleted from<br>later layers with small performance drops, which indicates spatial information<br>at later layers is not necessary for good performance. For example, test<br>accuracy of VGG-16 only drops by 0.03% and 2.66% with spatial information<br>completely removed from the last 30% and 53% layers on CIFAR100, respectively.<br>Evaluation on several object recognition datasets (CIFAR100, Small-ImageNet,<br>ImageNet) with a wide range of CNN architectures (VGG16, ResNet50, ResNet152)<br>shows an overall consistent pattern.<br>
Improved Methods and Analysis for Semantic Image Segmentation
Y. He
PhD Thesis, Universität des Saarlandes, 2020
Y. He
PhD Thesis, Universität des Saarlandes, 2020
Abstract
Modern deep learning has enabled amazing developments of computer vision in recent years (Hinton and Salakhutdinov, 2006; Krizhevsky et al., 2012). As a fundamental task, semantic segmentation aims to predict class labels for each pixel of images, which empowers machines perception of the visual world. In spite of recent successes of fully convolutional networks (Long etal., 2015), several challenges remain to be addressed. In this thesis, we focus on this topic, under different kinds of input formats and various types of scenes. Specifically, our study contains two aspects: (1) Data-driven neural modules for improved performance. (2) Leverage of datasets w.r.t.training systems with higher performances and better data privacy guarantees. In the first part of this thesis, we improve semantic segmentation by designing new modules which are compatible with existing architectures. First, we develop a spatio-temporal data-driven pooling, which brings additional information of data (i.e. superpixels) into neural networks, benefiting the training of neural networks as well as the inference on novel data. We investigate our approach in RGB-D videos for segmenting indoor scenes, where depth provides complementary cues to colors and our model performs particularly well. Second, we design learnable dilated convolutions, which are the extension of standard dilated convolutions, whose dilation factors (Yu and Koltun, 2016) need to be carefully determined by hand to obtain decent performance. We present a method to learn dilation factors together with filter weights of convolutions to avoid a complicated search of dilation factors. We explore extensive studies on challenging street scenes, across various baselines with different complexity as well as several datasets at varying image resolutions. In the second part, we investigate how to utilize expensive training data. First, we start from the generative modelling and study the network architectures and the learning pipeline for generating multiple examples. We aim to improve the diversity of generated examples but also to preserve the comparable quality of the examples. Second, we develop a generative model for synthesizing features of a network. With a mixture of real images and synthetic features, we are able to train a segmentation model with better generalization capability. Our approach is evaluated on different scene parsing tasks to demonstrate the effectiveness of the proposed method. Finally, we study membership inference on the semantic segmentation task. We propose the first membership inference attack system against black-box semantic segmentation models, that tries to infer if a data pair is used as training data or not. From our observations, information on training data is indeed leaking. To mitigate the leakage, we leverage our synthetic features to perform prediction obfuscations, reducing the posterior distribution gaps between a training and a testing set. Consequently, our study provides not only an approach for detecting illegal use of data, but also the foundations for a safer use of semantic segmentation models.
Towards Accurate Multi-Person Pose Estimation in the Wild
E. Insafutdinov
PhD Thesis, Universität des Saarlandes, 2020
E. Insafutdinov
PhD Thesis, Universität des Saarlandes, 2020
Multicut Optimization Guarantees & Geometry of Lifted Multicuts
J.-H. Lange
PhD Thesis, Universität des Saarlandes, 2020
J.-H. Lange
PhD Thesis, Universität des Saarlandes, 2020
Sensing, Interpreting, and Anticipating Human Social Behaviour in the Real World
P. Müller
PhD Thesis, Universität des Saarlandes, 2020
P. Müller
PhD Thesis, Universität des Saarlandes, 2020
Understanding and Controlling Leakage in Machine Learning
T. Orekondy
PhD Thesis, Universität des Saarlandes, 2020
T. Orekondy
PhD Thesis, Universität des Saarlandes, 2020
Learning from Limited Labeled Data - Zero-Shot and Few-Shot Learning
Y. Xian
PhD Thesis, Universität des Saarlandes, 2020
Y. Xian
PhD Thesis, Universität des Saarlandes, 2020
2019
LiveCap: Real-time Human Performance Capture from Monocular Video
M. Habermann, W. Xu, M. Zollhöfer, G. Pons-Moll and C. Theobalt
ACM Transactions on Graphics, Volume 38, Number 2, 2019
M. Habermann, W. Xu, M. Zollhöfer, G. Pons-Moll and C. Theobalt
ACM Transactions on Graphics, Volume 38, Number 2, 2019
Modeling Conceptual Understanding in Image Reference Games
R. Corona, S. Alaniz and Z. Akata
Advances in Neural Information Processing Systems 32 (NeurIPS 2019), 2019
R. Corona, S. Alaniz and Z. Akata
Advances in Neural Information Processing Systems 32 (NeurIPS 2019), 2019
Combining Generative and Discriminative Models for Hybrid Inference
V. Garcia Satorras, Z. Akata and M. Welling
Advances in Neural Information Processing Systems 32 (NeurIPS 2019), 2019
V. Garcia Satorras, Z. Akata and M. Welling
Advances in Neural Information Processing Systems 32 (NeurIPS 2019), 2019
Learning to Self-Train for Semi-Supervised Few-Shot Classification
X. Li, Q. Sun, Y. Liu, Q. Zhou, S. Zheng, T.-S. Chua and B. Schiele
Advances in Neural Information Processing Systems 32 (NeurIPS 2019), 2019
X. Li, Q. Sun, Y. Liu, Q. Zhou, S. Zheng, T.-S. Chua and B. Schiele
Advances in Neural Information Processing Systems 32 (NeurIPS 2019), 2019
Conditional Flow Variational Autoencoders for Structured Sequence Prediction
A. Bhattacharyya, M. Hanselmann, M. Fritz, B. Schiele and C.-N. Straehle
Bayesian Deep Learning NeurIPS 2019 Workshop, 2019
A. Bhattacharyya, M. Hanselmann, M. Fritz, B. Schiele and C.-N. Straehle
Bayesian Deep Learning NeurIPS 2019 Workshop, 2019
XNect Demo (v2): Real-time Multi-person 3D Human Pose Estimation with a Single RGB Camera
D. Mehta, O. Sotnychenko, F. Mueller, W. Xu, H.-P. Seidel, P. Fua, M. Elgharib, H. Rhodin, G. Pons-Moll and C. Theobalt
CVPR 2019 Demonstrations, 2019
D. Mehta, O. Sotnychenko, F. Mueller, W. Xu, H.-P. Seidel, P. Fua, M. Elgharib, H. Rhodin, G. Pons-Moll and C. Theobalt
CVPR 2019 Demonstrations, 2019
Emergent Leadership Detection Across Datasets
P. Müller and A. Bulling
ICMI ’19, International Conference on Multimodal Interaction, 2019
P. Müller and A. Bulling
ICMI ’19, International Conference on Multimodal Interaction, 2019
Abstract
Automatic detection of emergent leaders in small groups from nonverbal<br>behaviour is a growing research topic in social signal processing but existing<br>methods were evaluated on single datasets -- an unrealistic assumption for<br>real-world applications in which systems are required to also work in settings<br>unseen at training time. It therefore remains unclear whether current methods<br>for emergent leadership detection generalise to similar but new settings and to<br>which extent. To overcome this limitation, we are the first to study a<br>cross-dataset evaluation setting for the emergent leadership detection task. We<br>provide evaluations for within- and cross-dataset prediction using two current<br>datasets (PAVIS and MPIIGroupInteraction), as well as an investigation on the<br>robustness of commonly used feature channels (visual focus of attention, body<br>pose, facial action units, speaking activity) and online prediction in the<br>cross-dataset setting. Our evaluations show that using pose and eye contact<br>based features, cross-dataset prediction is possible with an accuracy of 0.68,<br>as such providing another important piece of the puzzle towards emergent<br>leadership detection in the real world.<br>
Learning to Reconstruct People in Clothing from a Single RGB Camera
T. Alldieck, M. A. Magnor, B. L. Bhatnagar, C. Theobalt and G. Pons-Moll
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019), 2019
T. Alldieck, M. A. Magnor, B. L. Bhatnagar, C. Theobalt and G. Pons-Moll
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019), 2019
In the Wild Human Pose Estimation using Explicit 2D Features and Intermediate 3D Representations
I. Habibie, W. Xu, D. Mehta, G. Pons-Moll and C. Theobalt
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019), 2019
I. Habibie, W. Xu, D. Mehta, G. Pons-Moll and C. Theobalt
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019), 2019
MAP Inference via Block-Coordinate Frank-Wolfe Algorithm
P. Swoboda and V. Kolmogorov
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019), 2019
P. Swoboda and V. Kolmogorov
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019), 2019
Abstract
When labeled training data is scarce, a promising data augmentation approach is to generate visual features of unknown classes using their attributes. To learn the class conditional distribution of CNN features, these models rely on pairs of image features and class attributes. Hence, they can not make use of the abundance of unlabeled data samples. In this paper, we tackle any-shot learning problems i.e. zero-shot and few-shot, in a unified feature generating framework that operates in both inductive and transductive learning settings. We develop a conditional generative model that combines the strength of VAE and GANs and in addition, via an unconditional discriminator, learns the marginal feature distribution of unlabeled images. We empirically show that our model learns highly discriminative CNN features for five datasets, i.e. CUB, SUN, AWA and ImageNet, and establish a new state-of-the-art in any-shot learning, i.e. inductive and transductive (generalized) zero- and few-shot learning settings. We also demonstrate that our learned features are interpretable: we visualize them by inverting them back to the pixel space and we explain them by generating textual arguments of why they are associated with a certain label.
A Convex Relaxation for Multi-Graph Matching
P. Swoboda, D. Kainmüller, A. Mokarian, C. Theobalt and F. Bernard
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019), 2019
P. Swoboda, D. Kainmüller, A. Mokarian, C. Theobalt and F. Bernard
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019), 2019
f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning
Y. Xian, S. Sharma, B. Schiele and Z. Akata
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019), 2019
Y. Xian, S. Sharma, B. Schiele and Z. Akata
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019), 2019
Abstract
When labeled training data is scarce, a promising data augmentation approach is to generate visual features of unknown classes using their attributes. To learn the class conditional distribution of CNN features, these models rely on pairs of image features and class attributes. Hence, they can not make use of the abundance of unlabeled data samples. In this paper, we tackle any-shot learning problems i.e. zero-shot and few-shot, in a unified feature generating framework that operates in both inductive and transductive learning settings. We develop a conditional generative model that combines the strength of VAE and GANs and in addition, via an unconditional discriminator, learns the marginal feature distribution of unlabeled images. We empirically show that our model learns highly discriminative CNN features for five datasets, i.e. CUB, SUN, AWA and ImageNet, and establish a new state-of-the-art in any-shot learning, i.e. inductive and transductive (generalized) zero- and few-shot learning settings. We also demonstrate that our learned features are interpretable: we visualize them by inverting them back to the pixel space and we explain them by generating textual arguments of why they are associated with a certain label.
Zero-shot Learning - A Comprehensive Evaluation of the Good, the Bad and the Ugly
Y. Xian, C. H. Lampert, B. Schiele and Z. Akata
IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 41, Number 9, 2019
Y. Xian, C. H. Lampert, B. Schiele and Z. Akata
IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 41, Number 9, 2019
Abstract
Due to the importance of zero-shot learning, i.e. classifying images where<br>there is a lack of labeled training data, the number of proposed approaches has<br>recently increased steadily. We argue that it is time to take a step back and<br>to analyze the status quo of the area. The purpose of this paper is three-fold.<br>First, given the fact that there is no agreed upon zero-shot learning<br>benchmark, we first define a new benchmark by unifying both the evaluation<br>protocols and data splits of publicly available datasets used for this task.<br>This is an important contribution as published results are often not comparable<br>and sometimes even flawed due to, e.g. pre-training on zero-shot test classes.<br>Moreover, we propose a new zero-shot learning dataset, the Animals with<br>Attributes 2 (AWA2) dataset which we make publicly available both in terms of<br>image features and the images themselves. Second, we compare and analyze a<br>significant number of the state-of-the-art methods in depth, both in the<br>classic zero-shot setting but also in the more realistic generalized zero-shot<br>setting. Finally, we discuss in detail the limitations of the current status of<br>the area which can be taken as a basis for advancing it.<br>
Tex2Shape: Detailed Full Human Body Geometry from a Single Image
T. Alldieck, G. Pons-Moll, C. Theobalt and M. A. Magnor
International Conference on Computer Vision (ICCV 2019), 2019
T. Alldieck, G. Pons-Moll, C. Theobalt and M. A. Magnor
International Conference on Computer Vision (ICCV 2019), 2019
Abstract
We present a simple yet effective method to infer detailed full human body<br>shape from only a single photograph. Our model can infer full-body shape<br>including face, hair, and clothing including wrinkles at interactive<br>frame-rates. Results feature details even on parts that are occluded in the<br>input image. Our main idea is to turn shape regression into an aligned<br>image-to-image translation problem. The input to our method is a partial<br>texture map of the visible region obtained from off-the-shelf methods. From a<br>partial texture, we estimate detailed normal and vector displacement maps,<br>which can be applied to a low-resolution smooth body model to add detail and<br>clothing. Despite being trained purely with synthetic data, our model<br>generalizes well to real-world photographs. Numerous results demonstrate the<br>versatility and robustness of our method.<br>
HiPPI: Higher-Order Projected Power Iterations for Scalable Multi-Matching
F. Bernard, J. Thunberg, P. Swoboda and C. Theobalt
International Conference on Computer Vision (ICCV 2019), 2019
F. Bernard, J. Thunberg, P. Swoboda and C. Theobalt
International Conference on Computer Vision (ICCV 2019), 2019
Bayesian Prediction of Future Street Scenes using Synthetic Likelihoods
A. Bhattacharyya, M. Fritz and B. Schiele
International Conference on Learning Representations (ICLR 2019), 2019
A. Bhattacharyya, M. Fritz and B. Schiele
International Conference on Learning Representations (ICLR 2019), 2019
Lucid Data Dreaming for Video Object Segmentation
A. Khoreva, R. Benenson, E. Ilg, T. Brox and B. Schiele
International Journal of Computer Vision, Volume 127, Number 9, 2019
A. Khoreva, R. Benenson, E. Ilg, T. Brox and B. Schiele
International Journal of Computer Vision, Volume 127, Number 9, 2019
Moment-to-Moment Detection of Internal Thought from Eye Vergence Behaviour
M. X. Huang, J. Li, G. Ngai, H. V. Leong and A. Bulling
MM ’19, 27th ACM International Conference on Multimedia, 2019
M. X. Huang, J. Li, G. Ngai, H. V. Leong and A. Bulling
MM ’19, 27th ACM International Conference on Multimedia, 2019
Abstract
Internal thought refers to the process of directing attention away from a<br>primary visual task to internal cognitive processing. Internal thought is a<br>pervasive mental activity and closely related to primary task performance. As<br>such, automatic detection of internal thought has significant potential for<br>user modelling in intelligent interfaces, particularly for e-learning<br>applications. Despite the close link between the eyes and the human mind, only<br>a few studies have investigated vergence behaviour during internal thought and<br>none has studied moment-to-moment detection of internal thought from gaze.<br>While prior studies relied on long-term data analysis and required a large<br>number of gaze characteristics, we describe a novel method that is<br>computationally light-weight and that only requires eye vergence information<br>that is readily available from binocular eye trackers. We further propose a<br>novel paradigm to obtain ground truth internal thought annotations that<br>exploits human blur perception. We evaluate our method for three increasingly<br>challenging detection tasks: (1) during a controlled math-solving task, (2)<br>during natural viewing of lecture videos, and (3) during daily activities, such<br>as coding, browsing, and reading. Results from these evaluations demonstrate<br>the performance and robustness of vergence-based detection of internal thought<br>and, as such, open up new directions for research on interfaces that adapt to<br>shifts of mental attention.<br>
Improving Language Generation from Feature-Rich Tree-Structured Data with Relational Graph Convolutional Encoders
X. Hong, E. Chang and V. Demberg
Multilingual Surface Realisation (MSR 2019), 2019
X. Hong, E. Chang and V. Demberg
Multilingual Surface Realisation (MSR 2019), 2019
SacCalib: Reducing Calibration Distortion for Stationary Eye Trackers Using Saccadic Eye Movements
M. X. Huang and A. Bulling
Proceedings ETRA 2019, 2019
M. X. Huang and A. Bulling
Proceedings ETRA 2019, 2019
Abstract
Recent methods to automatically calibrate stationary eye trackers were shown<br>to effectively reduce inherent calibration distortion. However, these methods<br>require additional information, such as mouse clicks or on-screen content. We<br>propose the first method that only requires users' eye movements to reduce<br>calibration distortion in the background while users naturally look at an<br>interface. Our method exploits that calibration distortion makes straight<br>saccade trajectories appear curved between the saccadic start and end points.<br>We show that this curving effect is systematic and the result of distorted gaze<br>projection plane. To mitigate calibration distortion, our method undistorts<br>this plane by straightening saccade trajectories using image warping. We show<br>that this approach improves over the common six-point calibration and is<br>promising for reducing distortion. As such, it provides a non-intrusive<br>solution to alleviating accuracy decrease of eye tracker during long-term use.<br>
Bottleneck Potentials in Markov Random Fields
A. Abbas and P. Swoboda
Technical Report, 2019
(arXiv: 1904.08080) A. Abbas and P. Swoboda
Technical Report, 2019
Abstract
We consider general discrete Markov Random Fields(MRFs) with additional<br>bottleneck potentials which penalize the maximum (instead of the sum) over<br>local potential value taken by the MRF-assignment. Bottleneck potentials or<br>analogous constructions have been considered in (i) combinatorial optimization<br>(e.g. bottleneck shortest path problem, the minimum bottleneck spanning tree<br>problem, bottleneck function minimization in greedoids), (ii) inverse problems<br>with $L_{\infty}$-norm regularization, and (iii) valued constraint satisfaction<br>on the $(\min,\max)$-pre-semirings. Bottleneck potentials for general discrete<br>MRFs are a natural generalization of the above direction of modeling work to<br>Maximum-A-Posteriori (MAP) inference in MRFs. To this end, we propose MRFs<br>whose objective consists of two parts: terms that factorize according to (i)<br>$(\min,+)$, i.e. potentials as in plain MRFs, and (ii) $(\min,\max)$, i.e.<br>bottleneck potentials. To solve the ensuing inference problem, we propose<br>high-quality relaxations and efficient algorithms for solving them. We<br>empirically show efficacy of our approach on large scale seismic horizon<br>tracking problems.<br>
“Best-of-Many-Samples” Distribution Matching
A. Bhattacharyya, M. Fritz and B. Schiele
Technical Report, 2019
(arXiv: 1909.12598) A. Bhattacharyya, M. Fritz and B. Schiele
Technical Report, 2019
Abstract
Generative Adversarial Networks (GANs) can achieve state-of-the-art sample<br>quality in generative modelling tasks but suffer from the mode collapse<br>problem. Variational Autoencoders (VAE) on the other hand explicitly maximize a<br>reconstruction-based data log-likelihood forcing it to cover all modes, but<br>suffer from poorer sample quality. Recent works have proposed hybrid VAE-GAN<br>frameworks which integrate a GAN-based synthetic likelihood to the VAE<br>objective to address both the mode collapse and sample quality issues, with<br>limited success. This is because the VAE objective forces a trade-off between<br>the data log-likelihood and divergence to the latent prior. The synthetic<br>likelihood ratio term also shows instability during training. We propose a<br>novel objective with a "Best-of-Many-Samples" reconstruction cost and a stable<br>direct estimate of the synthetic likelihood. This enables our hybrid VAE-GAN<br>framework to achieve high data log-likelihood and low divergence to the latent<br>prior at the same time and shows significant improvement over both hybrid<br>VAE-GANS and plain GANs in mode coverage and quality.<br>
LCC: Learning to Customize and Combine Neural Networks for Few-Shot Learning
Y. Liu, Q. Sun, A.-A. Liu, Y. Su, B. Schiele and T.-S. Chua
Technical Report, 2019
(arXiv: 1904.08479) Y. Liu, Q. Sun, A.-A. Liu, Y. Su, B. Schiele and T.-S. Chua
Technical Report, 2019
Abstract
Meta-learning has been shown to be an effective strategy for few-shot<br>learning. The key idea is to leverage a large number of similar few-shot tasks<br>in order to meta-learn how to best initiate a (single) base-learner for novel<br>few-shot tasks. While meta-learning how to initialize a base-learner has shown<br>promising results, it is well known that hyperparameter settings such as the<br>learning rate and the weighting of the regularization term are important to<br>achieve best performance. We thus propose to also meta-learn these<br>hyperparameters and in fact learn a time- and layer-varying scheme for learning<br>a base-learner on novel tasks. Additionally, we propose to learn not only a<br>single base-learner but an ensemble of several base-learners to obtain more<br>robust results. While ensembles of learners have shown to improve performance<br>in various settings, this is challenging for few-shot learning tasks due to the<br>limited number of training samples. Therefore, our approach also aims to<br>meta-learn how to effectively combine several base-learners. We conduct<br>extensive experiments and report top performance for five-class few-shot<br>recognition tasks on two challenging benchmarks: miniImageNet and<br>Fewshot-CIFAR100 (FC100).<br>
Learning Manipulation under Physics Constraints with Visual Perception
W. Li, A. Leonardis, J. Bohg and M. Fritz
Technical Report, 2019
(arXiv: 1904.09860) W. Li, A. Leonardis, J. Bohg and M. Fritz
Technical Report, 2019
Abstract
Understanding physical phenomena is a key competence that enables humans and<br>animals to act and interact under uncertain perception in previously unseen<br>environments containing novel objects and their configurations. In this work,<br>we consider the problem of autonomous block stacking and explore solutions to<br>learning manipulation under physics constraints with visual perception inherent<br>to the task. Inspired by the intuitive physics in humans, we first present an<br>end-to-end learning-based approach to predict stability directly from<br>appearance, contrasting a more traditional model-based approach with explicit<br>3D representations and physical simulation. We study the model's behavior<br>together with an accompanied human subject test. It is then integrated into a<br>real-world robotic system to guide the placement of a single wood block into<br>the scene without collapsing existing tower structure. To further automate the<br>process of consecutive blocks stacking, we present an alternative approach<br>where the model learns the physics constraint through the interaction with the<br>environment, bypassing the dedicated physics learning as in the former part of<br>this work. In particular, we are interested in the type of tasks that require<br>the agent to reach a given goal state that may be different for every new<br>trial. Thereby we propose a deep reinforcement learning framework that learns<br>policies for stacking tasks which are parametrized by a target structure.<br>
Interpretability Beyond Classification Output: Semantic Bottleneck Networks
M. Losch, M. Fritz and B. Schiele
Technical Report, 2019
(arXiv: 1907.10882) M. Losch, M. Fritz and B. Schiele
Technical Report, 2019
Abstract
Today's deep learning systems deliver high performance based on end-to-end<br>training. While they deliver strong performance, these systems are hard to<br>interpret. To address this issue, we propose Semantic Bottleneck Networks<br>(SBN): deep networks with semantically interpretable intermediate layers that<br>all downstream results are based on. As a consequence, the analysis on what the<br>final prediction is based on is transparent to the engineer and failure cases<br>and modes can be analyzed and avoided by high-level reasoning. We present a<br>case study on street scene segmentation to demonstrate the feasibility and<br>power of SBN. In particular, we start from a well performing classic deep<br>network which we adapt to house a SB-Layer containing task related semantic<br>concepts (such as object-parts and materials). Importantly, we can recover<br>state of the art performance despite a drastic dimensionality reduction from<br>1000s (non-semantic feature) to 10s (semantic concept) channels. Additionally<br>we show how the activations of the SB-Layer can be used for both the<br>interpretation of failure cases of the network as well as for confidence<br>prediction of the resulting output. For the first time, e.g., we show<br>interpretable segmentation results for most predictions at over 99% accuracy.<br>
A Novel BiLevel Paradigm for Image-to-Image Translation
L. Ma, Q. Sun, B. Schiele and L. Van Gool
Technical Report, 2019
(arXiv: 1904.09028) L. Ma, Q. Sun, B. Schiele and L. Van Gool
Technical Report, 2019
Abstract
Image-to-image (I2I) translation is a pixel-level mapping that requires a<br>large number of paired training data and often suffers from the problems of<br>high diversity and strong category bias in image scenes. In order to tackle<br>these problems, we propose a novel BiLevel (BiL) learning paradigm that<br>alternates the learning of two models, respectively at an instance-specific<br>(IS) and a general-purpose (GP) level. In each scene, the IS model learns to<br>maintain the specific scene attributes. It is initialized by the GP model that<br>learns from all the scenes to obtain the generalizable translation knowledge.<br>This GP initialization gives the IS model an efficient starting point, thus<br>enabling its fast adaptation to the new scene with scarce training data. We<br>conduct extensive I2I translation experiments on human face and street view<br>datasets. Quantitative results validate that our approach can significantly<br>boost the performance of classical I2I translation models, such as PG2 and<br>Pix2Pix. Our visualization results show both higher image quality and more<br>appropriate instance-specific details, e.g., the translated image of a person<br>looks more like that person in terms of identity.<br>
XNect: Real-time Multi-person 3D Human Pose Estimation with a Single RGB Camera
D. Mehta, O. Sotnychenko, F. Mueller, W. Xu, M. Elgharib, P. Fua, H.-P. Seidel, H. Rhodin, G. Pons-Moll and C. Theobalt
Technical Report, 2019
(arXiv: 1907.00837) D. Mehta, O. Sotnychenko, F. Mueller, W. Xu, M. Elgharib, P. Fua, H.-P. Seidel, H. Rhodin, G. Pons-Moll and C. Theobalt
Technical Report, 2019
Abstract
We present a real-time approach for multi-person 3D motion capture at over 30<br>fps using a single RGB camera. It operates in generic scenes and is robust to<br>difficult occlusions both by other people and objects. Our method operates in<br>subsequent stages. The first stage is a convolutional neural network (CNN) that<br>estimates 2D and 3D pose features along with identity assignments for all<br>visible joints of all individuals. We contribute a new architecture for this<br>CNN, called SelecSLS Net, that uses novel selective long and short range skip<br>connections to improve the information flow allowing for a drastically faster<br>network without compromising accuracy. In the second stage, a fully-connected<br>neural network turns the possibly partial (on account of occlusion) 2D pose and<br>3D pose features for each subject into a complete 3D pose estimate per<br>individual. The third stage applies space-time skeletal model fitting to the<br>predicted 2D and 3D pose per subject to further reconcile the 2D and 3D pose,<br>and enforce temporal coherence. Our method returns the full skeletal pose in<br>joint angles for each subject. This is a further key distinction from previous<br>work that neither extracted global body positions nor joint angle results of a<br>coherent skeleton in real time for multi-person scenes. The proposed system<br>runs on consumer hardware at a previously unseen speed of more than 30 fps<br>given 512x320 images as input while achieving state-of-the-art accuracy, which<br>we will demonstrate on a range of challenging real-world scenes.<br>
Shape Evasion: Preventing Body Shape Inference of Multi-Stage Approaches
H. Sattar, K. Krombholz, G. Pons-Moll and M. Fritz
Technical Report, 2019
(arXiv: 1905.11503) H. Sattar, K. Krombholz, G. Pons-Moll and M. Fritz
Technical Report, 2019
Abstract
Modern approaches to pose and body shape estimation have recently achieved<br>strong performance even under challenging real-world conditions. Even from a<br>single image of a clothed person, a realistic looking body shape can be<br>inferred that captures a users' weight group and body shape type well. This<br>opens up a whole spectrum of applications -- in particular in fashion -- where<br>virtual try-on and recommendation systems can make use of these new and<br>automatized cues. However, a realistic depiction of the undressed body is<br>regarded highly private and therefore might not be consented by most people.<br>Hence, we ask if the automatic extraction of such information can be<br>effectively evaded. While adversarial perturbations have been shown to be<br>effective for manipulating the output of machine learning models -- in<br>particular, end-to-end deep learning approaches -- state of the art shape<br>estimation methods are composed of multiple stages. We perform the first<br>investigation of different strategies that can be used to effectively<br>manipulate the automatic shape estimation while preserving the overall<br>appearance of the original image.<br>
Intents and Preferences Prediction Based on Implicit Human Cues
H. Sattar
PhD Thesis, Universität des Saarlandes, 2019
H. Sattar
PhD Thesis, Universität des Saarlandes, 2019
Abstract
Visual search is an important task, and it is part of daily human life. Thus, it has been a long-standing goal in Computer Vision to develop methods aiming at analysing human search intent and preferences. As the target of the search only exists in mind of the person, search intent prediction remains challenging for machine perception. In this thesis, we focus on advancing techniques for search target and preference prediction from implicit human cues. First, we propose a search target inference algorithm from human fixation data recorded during visual search. In contrast to previous work that has focused on individual instances as a search target in a closed world, we propose the first approach to predict the search target in open-world settings by learning the compatibility between observed fixations and potential search targets. Second, we further broaden the scope of search target prediction to categorical classes, such as object categories and attributes. However, state of the art models for categorical recognition, in general, require large amounts of training data, which is prohibitive for gaze data. To address this challenge, we propose a novel Gaze Pooling Layer that integrates gaze information into CNN-based architectures as an attention mechanism – incorporating both spatial and temporal aspects of human gaze behaviour. Third, we go one step further and investigate the feasibility of combining our gaze embedding approach, with the power of generative image models to visually decode, i.e. create a visual representation of, the search target. Forth, for the first time, we studied the effect of body shape on people preferences of outfits. We propose a novel and robust multi-photo approach to estimate the body shapes of each user and build a conditional model of clothing categories given body-shape. We demonstrate that in real-world data, clothing categories and body-shapes are correlated. We show that our approach estimates a realistic looking body shape that captures a user’s weight group and body shape type, even from a single image of a clothed person. However, an accurate depiction of the naked body is considered highly private and therefore, might not be consented by most people. First, we studied the perception of such technology via a user study. Then, in the last part of this thesis, we ask if the automatic extraction of such information can be effectively evaded. In summary, this thesis addresses several different tasks that aims to enable the vision system to analyse human search intent and preferences in real-world scenarios. In particular, the thesis proposes several novel ideas and models in visual search target prediction from human fixation data, for the first time studied the correlation between shape and clothing categories opening a new direction in clothing recommendation systems, and introduces a new topic in privacy and computer vision, aimed at preventing automatic 3D shape extraction from images.
Mobile Eye Tracking for Everyone
J. Steil
PhD Thesis, Universität des Saarlandes, 2019
J. Steil
PhD Thesis, Universität des Saarlandes, 2019
Abstract
Eye tracking and gaze-based human-computer interfaces have become a practical modality in desktop settings, since remote eye tracking is efficient and affordable. However, remote eye tracking remains constrained to indoor, laboratory-like conditions, in which lighting and user position need to be controlled. Mobile eye tracking has the potential to overcome these limitations and to allow people to move around freely and to use eye tracking on a daily basis during their everyday routine. However, mobile eye tracking currently faces two fundamental challenges that prevent it from being practically usable and that, consequently, have to be addressed before mobile eye tracking can truly be used by everyone: Mobile eye tracking needs to be advanced and made fully functional in unconstrained environments, and it needs to be made socially acceptable. Numerous sensing and analysis methods were initially developed for remote eye tracking and have been successfully applied for decades. Unfortunately, these methods are limited in terms of functionality and correctness, or even unsuitable for application in mobile eye tracking. Therefore, the majority of fundamental definitions, eye tracking methods, and gaze estimation approaches cannot be borrowed from remote eye tracking without adaptation. For example, the definitions of specific eye movements, like classical fixations, need to be extended to mobile settings where natural user and head motion are omnipresent. Corresponding analytical methods need to be adjusted or completely reimplemented based on novel approaches encoding the human gaze behaviour. Apart from these technical challenges, an entirely new, and yet under-explored, topic required for the breakthrough of mobile eye tracking as everyday technology is the overcoming of social obstacles. A first crucial key issue to defuse social objections is the building of acceptance towards mobile eye tracking. Hence, it is essential to replace the bulky appearance of current head-mounted eye trackers with an unobtrusive, appealing, and trendy design. The second high-priority theme of increasing importance for everyone is privacy and its protection, given that research and industry have not focused on or taken care of this problem at all. To establish true confidence, future devices have to find a fine balance between protecting users’ and bystanders’ privacy and attracting and convincing users of their necessity, utility, and potential with useful and beneficial features. The solution of technical challenges and social obstacles is the prerequisite for the development of a variety of novel and exciting applications in order to establish mobile eye tracking as a new paradigm, which ease our everyday life. This thesis addresses core technical challenges of mobile eye tracking that currently prevent it from being widely adopted. Specifically, this thesis proves that 3D data used for the calibration of mobile eye trackers improves gaze estimation and significantly reduces the parallax error. Further, it presents the first effective fixation detection method for head-mounted devices that is robust against the prevalence of user and gaze target motion. In order to achieve social acceptability, this thesis proposes an innovative and unobtrusive design for future mobile eye tracking devices and builds the first prototype with fully frame-embedded eye cameras combined with a calibration-free deep-trained appearance-based gaze estimation approach. To protect users’ and bystanders’ privacy in the presence of head-mounted eye trackers, this thesis presents another first-of-its-kind prototype. It is able to identify privacy-sensitive situations to automatically enable and disable the eye tracker’s first-person camera by means of a mechanical shutter, leveraging the combination of deep scene and eye movement features. Nevertheless, solving technical challenges and social obstacles alone is not sufficient to make mobile eye tracking attractive for the masses. The key to success is the development of convincingly useful, innovative, and essential applications. To extend the protection of users’ privacy on the software side as well, this thesis presents the first privacy-aware VR gaze interface using differential privacy. This method adds noise to recorded eye tracking data so that privacy-sensitive information like a user’s gender or identity is protected without impeding the utility of the data itself. In addition, the first large-scale online survey is conducted to understand users’ concerns with eye tracking. To develop and evaluate novel applications, this thesis presents the first publicly available long-term eye tracking datasets. They are used to show the unsupervised detection of users’ activities from eye movements alone using novel and efficient video-based encoding approaches as well as to propose the first proof-of-concept method to forecast users’ attentive behaviour during everyday mobile interactions from phone-integrated and body-worn sensors. This opens up possibilities for the development of a variety of novel and exciting applications. With more advanced features, accompanied by technological progress and sensor miniaturisation, eye tracking is increasingly integrated into conventional glasses as well as virtual and augmented reality (VR/AR) head-mounted displays, becoming an integral component of mobile interfaces. This thesis paves the way for the development of socially acceptable, privacy-aware, but highly functional mobile eye tracking devices and novel applications, so that mobile eye tracking can develop its full potential to become an everyday technology for everyone.
Confidence-Calibrated Adversarial Training and Detection: More Robust Models Generalizing Beyond the Attack Used During Training
D. Stutz, M. Hein and B. Schiele
Technical Report, 2019
(arXiv: 1910.06259) D. Stutz, M. Hein and B. Schiele
Technical Report, 2019
Abstract
Adversarial training is the standard to train models robust against<br>adversarial examples. However, especially for complex datasets, adversarial<br>training incurs a significant loss in accuracy and is known to generalize<br>poorly to stronger attacks, e.g., larger perturbations or other threat models.<br>In this paper, we introduce confidence-calibrated adversarial training (CCAT)<br>where the key idea is to enforce that the confidence on adversarial examples<br>decays with their distance to the attacked examples. We show that CCAT<br>preserves better the accuracy of normal training while robustness against<br>adversarial examples is achieved via confidence thresholding, i.e., detecting<br>adversarial examples based on their confidence. Most importantly, in strong<br>contrast to adversarial training, the robustness of CCAT generalizes to larger<br>perturbations and other threat models, not encountered during training. For<br>evaluation, we extend the commonly used robust test error to our detection<br>setting, present an adaptive attack with backtracking and allow the attacker to<br>select, per test example, the worst-case adversarial example from multiple<br>black- and white-box attacks. We present experimental results using $L_\infty$,<br>$L_2$, $L_1$ and $L_0$ attacks on MNIST, SVHN and Cifar10.<br>
2018
Sequential Attacks on Agents for Long-Term Adversarial Goals
E. Tretschk, S. J. Oh and M. Fritz
2. ACM Computer Science in Cars Symposium (CSCS 2018), 2018
E. Tretschk, S. J. Oh and M. Fritz
2. ACM Computer Science in Cars Symposium (CSCS 2018), 2018
Unsupervised Learning of Shape and Pose with Differentiable Point Clouds
E. Insafutdinov and A. Dosovitskiy
Advances in Neural Information Processing Systems 31 (NeurIPS 2018), 2018
E. Insafutdinov and A. Dosovitskiy
Advances in Neural Information Processing Systems 31 (NeurIPS 2018), 2018
Adversarial Scene Editing: Automatic Object Removal from Weak Supervision
R. Shetty, M. Fritz and B. Schiele
Advances in Neural Information Processing Systems 31 (NeurIPS 2018), 2018
R. Shetty, M. Fritz and B. Schiele
Advances in Neural Information Processing Systems 31 (NeurIPS 2018), 2018
Abstract
While great progress has been made recently in automatic image manipulation,<br>it has been limited to object centric images like faces or structured scene<br>datasets. In this work, we take a step towards general scene-level image<br>editing by developing an automatic interaction-free object removal model. Our<br>model learns to find and remove objects from general scene images using<br>image-level labels and unpaired data in a generative adversarial network (GAN)<br>framework. We achieve this with two key contributions: a two-stage editor<br>architecture consisting of a mask generator and image in-painter that<br>co-operate to remove objects, and a novel GAN based prior for the mask<br>generator that allows us to flexibly incorporate knowledge about object shapes.<br>We experimentally show on two datasets that our method effectively removes a<br>wide variety of objects using weak supervision only<br>
JAMI: Fast Computation of Conditional Mutual Information for ceRNA Network Analysis
A. Horňáková, M. List, J. Vreeken and M. H. Schulz
Bioinformatics, Volume 34, Number 17, 2018
A. Horňáková, M. List, J. Vreeken and M. H. Schulz
Bioinformatics, Volume 34, Number 17, 2018
Textual Explanations for Self-Driving Vehicles
J. Kim, A. Rohrbach, T. Darrell, J. Canny and Z. Akata
Computer Vision -- ECCV 2018, 2018
J. Kim, A. Rohrbach, T. Darrell, J. Canny and Z. Akata
Computer Vision -- ECCV 2018, 2018
Abstract
Deep neural perception and control networks have become key com-<br>ponents of self-driving vehicles. User acceptance is likely to benefit from easy-<br>to-interpret textual explanations which allow end-users to understand what trig-<br>gered a particular behavior. Explanations may be triggered by the neural con-<br>troller, namely<br>introspective explanations<br>, or informed by the neural controller’s<br>output, namely<br>rationalizations<br>. We propose a new approach to introspective ex-<br>planations which consists of two parts. First, we use a visual (spatial) attention<br>model to train a convolutional network end-to-end from images to the vehicle<br>control commands,<br>i<br>.<br>e<br>., acceleration and change of course. The controller’s at-<br>tention identifies image regions that potentially influence the network’s output.<br>Second, we use an attention-based video-to-text model to produce textual ex-<br>planations of model actions. The attention maps of controller and explanation<br>model are aligned so that explanations are grounded in the parts of the scene that<br>mattered to the controller. We explore two approaches to attention alignment,<br>strong- and weak-alignment. Finally, we explore a version of our model that<br>generates rationalizations, and compare with introspective explanations on the<br>same video segments. We evaluate these models on a novel driving dataset with<br>ground-truth human explanations, the Berkeley DeepDrive eXplanation (BDD-<br>X) dataset. Code is available at<br>https://github.com/JinkyuKimUCB/explainable-deep-driving
A Vision-grounded Dataset for Predicting Typical Locations for Verbs
N. Mukuze, A. Rohrbach, V. Demberg and B. Schiele
Eleventh International Conference on Language Resources and Evaluation (LREC 2018), 2018
N. Mukuze, A. Rohrbach, V. Demberg and B. Schiele
Eleventh International Conference on Language Resources and Evaluation (LREC 2018), 2018
Eye Movements During Everyday Behavior Predict Personality Traits
S. Hoppe, T. Loetscher, S. Morey and A. Bulling
Frontiers in Human Neuroscience, Volume 12, 2018
S. Hoppe, T. Loetscher, S. Morey and A. Bulling
Frontiers in Human Neuroscience, Volume 12, 2018
Learning to Refine Human Pose Estimation
M. Fieraru, A. Khoreva, L. Pishchulin and B. Schiele
IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2018), 2018
M. Fieraru, A. Khoreva, L. Pishchulin and B. Schiele
IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2018), 2018
Towards Reaching Human Performance in Pedestrian Detection
S. Zhang, R. Benenson, M. Omran, J. Hosang and B. Schiele
IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 40, Number 4, 2018
S. Zhang, R. Benenson, M. Omran, J. Hosang and B. Schiele
IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 40, Number 4, 2018
Abstract
Encouraged by the recent progress in pedestrian detection, we investigate the gap between current state-of-the-art methods
and the “perfect single frame detector”. We enable our analysis by creating a human baseline for pedestrian detection (over the Caltech
pedestrian dataset). After manually clustering the frequent errors of a top detector, we characterise both localisation and background-
versus-foreground errors.
To address localisation errors we study the impact of training annotation noise on the detector performance, and show that we can
improve results even with a small portion of sanitised training data. To address background/foreground discrimination, we study convnets
for pedestrian detection, and discuss which factors affect their performance.
Other than our in-depth analysis, we report top performance on the Caltech pedestrian dataset, and provide a new sanitised set of
training and test annotations.
Learning 3D Shape Completion under Weak Supervision
D. Stutz and A. Geiger
International Journal of Computer Vision, Volume 128, 2018
D. Stutz and A. Geiger
International Journal of Computer Vision, Volume 128, 2018
NRST: Non-rigid Surface Tracking from Monocular Video
M. Habermann, W. Xu, H. Rohdin, M. Zollhöfer, G. Pons-Moll and C. Theobalt
Pattern Recognition (GCPR 2018), 2018
M. Habermann, W. Xu, H. Rohdin, M. Zollhöfer, G. Pons-Moll and C. Theobalt
Pattern Recognition (GCPR 2018), 2018
A4NT: Author Attribute Anonymity by Adversarial Training of Neural Machine Translation
R. Shetty, B. Schiele and M. Fritz
Proceedings of the 27th USENIX Security Symposium, 2018
R. Shetty, B. Schiele and M. Fritz
Proceedings of the 27th USENIX Security Symposium, 2018
Partial Optimality and Fast Lower Bounds for Weighted Correlation Clustering
J.-H. Lange, A. Karrenbauer and B. Andres
Proceedings of the 35th International Conference on Machine Learning (ICML 2018), 2018
J.-H. Lange, A. Karrenbauer and B. Andres
Proceedings of the 35th International Conference on Machine Learning (ICML 2018), 2018
A Multimodal Corpus of Expert Gaze and Behavior during Phonetic Segmentation Tasks
A. Khan, I. Steiner, Y. Sugano, A. Bulling and R. Macdonald
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), 2018
A. Khan, I. Steiner, Y. Sugano, A. Bulling and R. Macdonald
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), 2018
Generating Counterfactual Explanations with Natural Language
L. A. Hendricks, R. Hu, T. Darrell and Z. Akata
Proceedings of the 2018 ICML Workshop on Human Interpretability in Machine Learning (WHI 2018), 2018
(arXiv: 1806.09809) L. A. Hendricks, R. Hu, T. Darrell and Z. Akata
Proceedings of the 2018 ICML Workshop on Human Interpretability in Machine Learning (WHI 2018), 2018
Abstract
Natural language explanations of deep neural network decisions provide an<br>intuitive way for a AI agent to articulate a reasoning process. Current textual<br>explanations learn to discuss class discriminative features in an image.<br>However, it is also helpful to understand which attributes might change a<br>classification decision if present in an image (e.g., "This is not a Scarlet<br>Tanager because it does not have black wings.") We call such textual<br>explanations counterfactual explanations, and propose an intuitive method to<br>generate counterfactual explanations by inspecting which evidence in an input<br>is missing, but might contribute to a different classification decision if<br>present in the image. To demonstrate our method we consider a fine-grained<br>image classification task in which we take as input an image and a<br>counterfactual class and output text which explains why the image does not<br>belong to a counterfactual class. We then analyze our generated counterfactual<br>explanations both qualitatively and quantitatively using proposed automatic<br>metrics.<br>
Advanced Steel Microstructure Classification by Deep Learning Methods
S. M. Azimi, D. Britz, M. Engstler, M. Fritz and F. Mücklich
Scientific Reports, Volume 8, 2018
S. M. Azimi, D. Britz, M. Engstler, M. Fritz and F. Mücklich
Scientific Reports, Volume 8, 2018
Abstract
The inner structure of a material is called microstructure. It stores the
genesis of a material and determines all its physical and chemical properties.
While microstructural characterization is widely spread and well known, the
microstructural classification is mostly done manually by human experts, which
opens doors for huge uncertainties. Since the microstructure could be a
combination of different phases with complex substructures its automatic
classification is very challenging and just a little work in this field has
been carried out. Prior related works apply mostly designed and engineered
features by experts and classify microstructure separately from feature
extraction step. Recently Deep Learning methods have shown surprisingly good
performance in vision applications by learning the features from data together
with the classification step. In this work, we propose a deep learning method
for microstructure classification in the examples of certain microstructural
constituents of low carbon steel. This novel method employs pixel-wise
segmentation via Fully Convolutional Neural Networks (FCNN) accompanied by
max-voting scheme. Our system achieves 93.94% classification accuracy,
drastically outperforming the state-of-the-art method of 48.89% accuracy,
indicating the effectiveness of pixel-wise approaches. Beyond the success
presented in this paper, this line of research offers a more robust and first
of all objective way for the difficult task of steel quality appreciation.
Towards Reverse-Engineering Black-Box Neural Networks
S. J. Oh, M. Augustin, B. Schiele and M. Fritz
Sixth International Conference on Learning Representations (ICLR 2018), 2018
S. J. Oh, M. Augustin, B. Schiele and M. Fritz
Sixth International Conference on Learning Representations (ICLR 2018), 2018
Higher-order Projected Power Iterations for Scalable Multi-Matching
F. Bernard, J. Thunberg, P. Swoboda and C. Theobalt
Technical Report, 2018
(arXiv: 1811.10541) F. Bernard, J. Thunberg, P. Swoboda and C. Theobalt
Technical Report, 2018
Abstract
The matching of multiple objects (e.g. shapes or images) is a fundamental<br>problem in vision and graphics. In order to robustly handle ambiguities, noise<br>and repetitive patterns in challenging real-world settings, it is essential to<br>take geometric consistency between points into account. Computationally, the<br>multi-matching problem is difficult. It can be phrased as simultaneously<br>solving multiple (NP-hard) quadratic assignment problems (QAPs) that are<br>coupled via cycle-consistency constraints. The main limitations of existing<br>multi-matching methods are that they either ignore geometric consistency and<br>thus have limited robustness, or they are restricted to small-scale problems<br>due to their (relatively) high computational cost. We address these<br>shortcomings by introducing a Higher-order Projected Power Iteration method,<br>which is (i) efficient and scales to tens of thousands of points, (ii)<br>straightforward to implement, (iii) able to incorporate geometric consistency,<br>and (iv) guarantees cycle-consistent multi-matchings. Experimentally we show<br>that our approach is superior to existing methods.<br>
Bayesian Prediction of Future Street Scenes through Importance Sampling based Optimization
A. Bhattacharyya, M. Fritz and B. Schiele
Technical Report, 2018
(arXiv: 1806.06939) A. Bhattacharyya, M. Fritz and B. Schiele
Technical Report, 2018
Abstract
For autonomous agents to successfully operate in the real world, anticipation
of future events and states of their environment is a key competence. This
problem can be formalized as a sequence prediction problem, where a number of
observations are used to predict the sequence into the future. However,
real-world scenarios demand a model of uncertainty of such predictions, as
future states become increasingly uncertain and multi-modal -- in particular on
long time horizons. This makes modelling and learning challenging. We cast
state of the art semantic segmentation and future prediction models based on
deep learning into a Bayesian formulation that in turn allows for a full
Bayesian treatment of the prediction problem. We present a new sampling scheme
for this model that draws from the success of variational autoencoders by
incorporating a recognition network. In the experiments we show that our model
outperforms prior work in accuracy of the predicted segmentation and provides
calibrated probabilities that also better capture the multi-modal aspects of
possible future states of street scenes.
Primal-Dual Wasserstein GAN
M. Gemici, Z. Akata and M. Welling
Technical Report, 2018
(arXiv: 1805.09575) M. Gemici, Z. Akata and M. Welling
Technical Report, 2018
Abstract
We introduce Primal-Dual Wasserstein GAN, a new learning algorithm for
building latent variable models of the data distribution based on the primal
and the dual formulations of the optimal transport (OT) problem. We utilize the
primal formulation to learn a flexible inference mechanism and to create an
optimal approximate coupling between the data distribution and the generative
model. In order to learn the generative model, we use the dual formulation and
train the decoder adversarially through a critic network that is regularized by
the approximate coupling obtained from the primal. Unlike previous methods that
violate various properties of the optimal critic, we regularize the norm and
the direction of the gradients of the critic function. Our model shares many of
the desirable properties of auto-encoding models in terms of mode coverage and
latent structure, while avoiding their undesirable averaging properties, e.g.
their inability to capture sharp visual features when modeling real images. We
compare our algorithm with several other generative modeling techniques that
utilize Wasserstein distances on Frechet Inception Distance (FID) and Inception
Scores (IS).
MLCapsule: Guarded Offline Deployment of Machine Learning as a Service
L. Hanzlik, Y. Zhang, K. Grosse, A. Salem, M. Augustin, M. Backes and M. Fritz
Technical Report, 2018
(arXiv: 1808.00590) L. Hanzlik, Y. Zhang, K. Grosse, A. Salem, M. Augustin, M. Backes and M. Fritz
Technical Report, 2018
Abstract
With the widespread use of machine learning (ML) techniques, ML as a service<br>has become increasingly popular. In this setting, an ML model resides on a<br>server and users can query the model with their data via an API. However, if<br>the user's input is sensitive, sending it to the server is not an option.<br>Equally, the service provider does not want to share the model by sending it to<br>the client for protecting its intellectual property and pay-per-query business<br>model. In this paper, we propose MLCapsule, a guarded offline deployment of<br>machine learning as a service. MLCapsule executes the machine learning model<br>locally on the user's client and therefore the data never leaves the client.<br>Meanwhile, MLCapsule offers the service provider the same level of control and<br>security of its model as the commonly used server-side execution. In addition,<br>MLCapsule is applicable to offline applications that require local execution.<br>Beyond protecting against direct model access, we demonstrate that MLCapsule<br>allows for implementing defenses against advanced attacks on machine learning<br>models such as model stealing/reverse engineering and membership inference.<br>
Manipulating Attributes of Natural Scenes via Hallucination
L. Karacan, Z. Akata, A. Erdem and E. Erdem
Technical Report, 2018
(arXiv: 1808.07413) L. Karacan, Z. Akata, A. Erdem and E. Erdem
Technical Report, 2018
Abstract
In this study, we explore building a two-stage framework for enabling users
to directly manipulate high-level attributes of a natural scene. The key to our
approach is a deep generative network which can hallucinate images of a scene
as if they were taken at a different season (e.g. during winter), weather
condition (e.g. in a cloudy day) or time of the day (e.g. at sunset). Once the
scene is hallucinated with the given attributes, the corresponding look is then
transferred to the input image while preserving the semantic details intact,
giving a photo-realistic manipulation result. As the proposed framework
hallucinates what the scene will look like, it does not require any reference
style image as commonly utilized in most of the appearance or style transfer
approaches. Moreover, it allows to simultaneously manipulate a given scene
according to a diverse set of transient attributes within a single model,
eliminating the need of training multiple networks per each translation task.
Our comprehensive set of qualitative and quantitative results demonstrate the
effectiveness of our approach against the competing methods.
Learning a Disentangled Embedding for Monocular 3D Shape Retrieval and Pose Estimation
K. Z. Lin, W. Xu, Q. Sun, C. Theobalt and T.-S. Chua
Technical Report, 2018
(arXiv: 1812.09899) K. Z. Lin, W. Xu, Q. Sun, C. Theobalt and T.-S. Chua
Technical Report, 2018
Abstract
We propose a novel approach to jointly perform 3D object retrieval and pose<br>estimation from monocular images.In order to make the method robust to real<br>world scene variations in the images, e.g. texture, lighting and background,we<br>learn an embedding space from 3D data that only includes the relevant<br>information, namely the shape and pose.Our method can then be trained for<br>robustness under real world scene variations without having to render a large<br>training set simulating these variations. Our learned embedding explicitly<br>disentangles a shape vector and a pose vector, which alleviates both pose bias<br>for 3D shape retrieval and categorical bias for pose estimation. Having the<br>learned disentangled embedding, we train a CNN to map the images to the<br>embedding space, and then retrieve the closest 3D shape from the database and<br>estimate the 6D pose of the object using the embedding vectors. Our method<br>achieves 10.8 median error for pose estimation and 0.514 top-1-accuracy for<br>category agnostic 3D object retrieval on the Pascal3D+ dataset. It therefore<br>outperforms the previous state-of-the-art methods on both tasks.<br>
From Perception over Anticipation to Manipulation
W. Li
PhD Thesis, Universität des Saarlandes, 2018
W. Li
PhD Thesis, Universität des Saarlandes, 2018
Abstract
From autonomous driving cars to surgical robots, robotic system has enjoyed significant growth over the past decade. With the rapid development in robotics alongside the evolution in the related fields, such as computer vision and machine learning, integrating perception, anticipation and manipulation is key to the success of future robotic system. In this thesis, we explore different ways of such integration to extend the capabilities of a robotic system to take on more challenging real world tasks. On anticipation and perception, we address the recognition of ongoing activity from videos. In particular we focus on long-duration and complex activities and hence propose a new challenging dataset to facilitate the work. We introduce hierarchical labels over the activity classes and investigate the temporal accuracy-specificity trade-offs. We propose a new method based on recurrent neural networks that learns to predict over this hierarchy and realize accuracy specificity trade-offs. Our method outperforms several baselines on this new challenge. On manipulation with perception, we propose an efficient framework for programming a robot to use human tools. We first present a novel and compact model for using tools described by a tip model. Then we explore a strategy of utilizing a dual-gripper approach for manipulating tools – motivated by the absence of dexterous hands on widely available general purpose robots. Afterwards, we embed the tool use learning into a hierarchical architecture and evaluate it on a Baxter research robot. Finally, combining perception, anticipation and manipulation, we focus on a block stacking task. First we explore how to guide robot to place a single block into the scene without collapsing the existing structure. We introduce a mechanism to predict physical stability directly from visual input and evaluate it first on a synthetic data and then on real-world block stacking. Further, we introduce the target stacking task where the agent stacks blocks to reproduce a tower shown in an image. To do so, we create a synthetic block stacking environment with physics simulation in which the agent can learn block stacking end-to-end through trial and error, bypassing to explicitly model the corresponding physics knowledge. We propose a goal-parametrized GDQN model to plan with respect to the specific goal. We validate the model on both a navigation task in a classic gridworld environment and the block stacking task.
Deep Appearance Maps
M. Maximov, T. Ritschel and M. Fritz
Technical Report, 2018
(arXiv: 1804.00863) M. Maximov, T. Ritschel and M. Fritz
Technical Report, 2018
Abstract
We propose a deep representation of appearance, i. e. the relation of color,
surface orientation, viewer position, material and illumination. Previous
approaches have used deep learning to extract classic appearance
representations relating to reflectance model parameters (e. g. Phong) or
illumination (e. g. HDR environment maps). We suggest to directly represent
appearance itself as a network we call a deep appearance map (DAM). This is a
4D generalization over 2D reflectance maps, which held the view direction
fixed. First, we show how a DAM can be learned from images or video frames and
later be used to synthesize appearance, given new surface orientations and
viewer positions. Second, we demonstrate how another network can be used to map
from an image or video frames to a DAM network to reproduce this appearance,
without using a lengthy optimization such as stochastic gradient descent
(learning-to-learn). Finally, we generalize this to an appearance
estimation-and-segmentation task, where we map from an image showing multiple
materials to multiple networks reproducing their appearance, as well as
per-pixel segmentation.
Image Manipulation against Learned Models Privacy and Security Implications
S. J. Oh
PhD Thesis, Universität des Saarlandes, 2018
S. J. Oh
PhD Thesis, Universität des Saarlandes, 2018
Abstract
Machine learning is transforming the world. Its application areas span privacy<br>sensitive and security critical tasks such as human identification and self-driving<br>cars. These applications raise privacy and security related questions that are not<br>fully understood or answered yet: Can automatic person recognisers identify people<br>in photos even when their faces are blurred? How easy is it to find an adversarial<br>input for a self-driving car that makes it drive off the road?<br>This thesis contributes one of the first steps towards a better understanding of<br>such concerns. We observe that many privacy and security critical scenarios for<br>learned models involve input data manipulation: users obfuscate their identity by<br>blurring their faces and adversaries inject imperceptible perturbations to the input<br>signal. We introduce a data manipulator framework as a tool for collectively describing<br>and analysing privacy and security relevant scenarios involving learned models.<br>A data manipulator introduces a shift in data distribution for achieving privacy or<br>security related goals, and feeds the transformed input to the target model. This<br>framework provides a common perspective on the studies presented in the thesis.<br>We begin the studies from the user’s privacy point of view. We analyse the<br>efficacy of common obfuscation methods like face blurring, and show that they<br>are surprisingly ineffective against state of the art person recognition systems. We<br>then propose alternatives based on head inpainting and adversarial examples. By<br>studying the user privacy, we also study the dual problem: model security. In model<br>security perspective, a model ought to be robust and reliable against small amounts<br>of data manipulation. In both cases, data are manipulated with the goal of changing<br>the target model prediction. User privacy and model security problems can be<br>described with the same objective.<br>We then study the knowledge aspect of the data manipulation problem. The more<br>one knows about the target model, the more effective manipulations one can craft.<br>We propose a game theoretic manipulation framework to systematically represent<br>the knowledge level on the target model and derive privacy and security guarantees.<br>We then discuss ways to increase knowledge about a black-box model by only querying<br>it, deriving implications that are relevant to both privacy and security perspectives.
Understanding and Controlling User Linkability in Decentralized Learning
T. Orekondy, S. J. Oh, B. Schiele and M. Fritz
Technical Report, 2018
(arXiv: 1805.05838) T. Orekondy, S. J. Oh, B. Schiele and M. Fritz
Technical Report, 2018
Abstract
Machine Learning techniques are widely used by online services (e.g. Google,
Apple) in order to analyze and make predictions on user data. As many of the
provided services are user-centric (e.g. personal photo collections, speech
recognition, personal assistance), user data generated on personal devices is
key to provide the service. In order to protect the data and the privacy of the
user, federated learning techniques have been proposed where the data never
leaves the user's device and "only" model updates are communicated back to the
server. In our work, we propose a new threat model that is not concerned with
learning about the content - but rather is concerned with the linkability of
users during such decentralized learning scenarios.
We show that model updates are characteristic for users and therefore lend
themselves to linkability attacks. We show identification and matching of users
across devices in closed and open world scenarios. In our experiments, we find
our attacks to be highly effective, achieving 20x-175x chance-level
performance.
In order to mitigate the risks of linkability attacks, we study various
strategies. As adding random noise does not offer convincing operation points,
we propose strategies based on using calibrated domain-specific data; we find
these strategies offers substantial protection against linkability threats with
little effect to utility.
End-to-end Learning for Graph Decomposition
J. Song, B. Andres, M. Black, O. Hilliges and S. Tang
Technical Report, 2018
(arXiv: 1812.09737) J. Song, B. Andres, M. Black, O. Hilliges and S. Tang
Technical Report, 2018
Abstract
We propose a novel end-to-end trainable framework for the graph decomposition<br>problem. The minimum cost multicut problem is first converted to an<br>unconstrained binary cubic formulation where cycle consistency constraints are<br>incorporated into the objective function. The new optimization problem can be<br>viewed as a Conditional Random Field (CRF) in which the random variables are<br>associated with the binary edge labels of the initial graph and the hard<br>constraints are introduced in the CRF as high-order potentials. The parameters<br>of a standard Neural Network and the fully differentiable CRF are optimized in<br>an end-to-end manner. Furthermore, our method utilizes the cycle constraints as<br>meta-supervisory signals during the learning of the deep feature<br>representations by taking the dependencies between the output random variables<br>into account. We present analyses of the end-to-end learned representations,<br>showing the impact of the joint training, on the task of clustering images of<br>MNIST. We also validate the effectiveness of our approach both for the feature<br>learning and the final clustering on the challenging task of real-world<br>multi-person pose estimation.<br>
PrivacEye: Privacy-Preserving First-Person Vision Using Image Features and Eye Movement Analysis
J. Steil, M. Koelle, W. Heuten, S. Boll and A. Bulling
Technical Report, 2018
(arXiv: 1801.04457) J. Steil, M. Koelle, W. Heuten, S. Boll and A. Bulling
Technical Report, 2018
Abstract
As first-person cameras in head-mounted displays become increasingly
prevalent, so does the problem of infringing user and bystander privacy. To
address this challenge, we present PrivacEye, a proof-of-concept system that
detects privacysensitive everyday situations and automatically enables and
disables the first-person camera using a mechanical shutter. To close the
shutter, PrivacEye detects sensitive situations from first-person camera videos
using an end-to-end deep-learning model. To open the shutter without visual
input, PrivacEye uses a separate, smaller eye camera to detect changes in
users' eye movements to gauge changes in the "privacy level" of the current
situation. We evaluate PrivacEye on a dataset of first-person videos recorded
in the daily life of 17 participants that they annotated with privacy
sensitivity levels. We discuss the strengths and weaknesses of our
proof-of-concept system based on a quantitative technical evaluation as well as
qualitative insights from semi-structured interviews.
Gaze Estimation and Interaction in Real-World Environments
X. Zhang
PhD Thesis, Universität des Saarlandes, 2018
X. Zhang
PhD Thesis, Universität des Saarlandes, 2018
Abstract
Following a period of expedited progress in the capabilities of digital systems, the society begins to realize that systems designed to assist people in various tasks can also harm individuals and society. Mediating access to information and explicitly or implicitly ranking people in increasingly many applications, search systems have a substantial potential to contribute to such unwanted outcomes. Since they collect vast amounts of data about both searchers and search subjects, they have the potential to violate the privacy of both of these groups of users. Moreover, in applications where rankings influence people's economic livelihood outside of the platform, such as sharing economy or hiring support websites, search engines have an immense economic power over their users in that they control user exposure in ranked results. This thesis develops new models and methods broadly covering different aspects of privacy and fairness in search systems for both searchers and search subjects. Specifically, it makes the following contributions: (1) We propose a model for computing individually fair rankings where search subjects get exposure proportional to their relevance. The exposure is amortized over time using constrained optimization to overcome searcher attention biases while preserving ranking utility. (2) We propose a model for computing sensitive search exposure where each subject gets to know the sensitive queries that lead to her profile in the top-k search results. The problem of finding exposing queries is technically modeled as reverse nearest neighbor search, followed by a weekly-supervised learning to rank model ordering the queries by privacy-sensitivity. (3) We propose a model for quantifying privacy risks from textual data in online communities. The method builds on a topic model where each topic is annotated by a crowdsourced sensitivity score, and privacy risks are associated with a user's relevance to sensitive topics. We propose relevance measures capturing different dimensions of user interest in a topic and show how they correlate with human risk perceptions. (4) We propose a model for privacy-preserving personalized search where search queries of different users are split and merged into synthetic profiles. The model mediates the privacy-utility trade-off by keeping semantically coherent fragments of search histories within individual profiles, while trying to minimize the similarity of any of the synthetic profiles to the original user profiles. The models are evaluated using information retrieval techniques and user studies over a variety of datasets, ranging from query logs, through social media and community question answering postings, to item listings from sharing economy platforms.
2017
Long-Term On-Board Prediction of Pedestrians in Traffic Scenes
A. Bhattacharyya, M. Fritz and B. Schiele
1st Conference on Robot Learning (CoRL 2017), 2017
A. Bhattacharyya, M. Fritz and B. Schiele
1st Conference on Robot Learning (CoRL 2017), 2017
Gradient-free Policy Architecture Search and Adaptation
S. Ebrahimi, A. Rohrbach and T. Darrell
1st Conference on Robot Learning (CoRL 2017), 2017
S. Ebrahimi, A. Rohrbach and T. Darrell
1st Conference on Robot Learning (CoRL 2017), 2017
CityPersons: A Diverse Dataset for Pedestrian Detection
S. Zhang, R. Benenson and B. Schiele
30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017), 2017
S. Zhang, R. Benenson and B. Schiele
30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017), 2017
Abstract
Convnets have enabled significant progress in pedestrian detection recently,
but there are still open questions regarding suitable architectures and
training data. We revisit CNN design and point out key adaptations, enabling
plain FasterRCNN to obtain state-of-the-art results on the Caltech dataset.
To achieve further improvement from more and better data, we introduce
CityPersons, a new set of person annotations on top of the Cityscapes dataset.
The diversity of CityPersons allows us for the first time to train one single
CNN model that generalizes well over multiple benchmarks. Moreover, with
additional training with CityPersons, we obtain top results using FasterRCNN on
Caltech, improving especially for more difficult cases (heavy occlusion and
small scale) and providing higher localization quality.
Visual Stability Prediction and Its Application to Manipulation
W. Li, A. Leonardis and M. Fritz
AAAI 2017 Spring Symposia 05, Interactive Multisensory Object Perception for Embodied Agents, 2017
W. Li, A. Leonardis and M. Fritz
AAAI 2017 Spring Symposia 05, Interactive Multisensory Object Perception for Embodied Agents, 2017
Pose Guided Person Image Generation
L. Ma, X. Jia, Q. Sun, B. Schiele, T. Tuytelaars and L. Van Gool
Advances in Neural Information Processing Systems 30 (NIPS 2017), 2017
L. Ma, X. Jia, Q. Sun, B. Schiele, T. Tuytelaars and L. Van Gool
Advances in Neural Information Processing Systems 30 (NIPS 2017), 2017
Lucid Data Dreaming for Object Tracking
A. Khoreva, R. Benenson, E. Ilg, T. Brox and B. Schiele
DAVIS Challenge on Video Object Segmentation 2017, 2017
A. Khoreva, R. Benenson, E. Ilg, T. Brox and B. Schiele
DAVIS Challenge on Video Object Segmentation 2017, 2017
Predicting the Category and Attributes of Visual Search Targets Using Deep Gaze Pooling
H. Sattar, A. Bulling and M. Fritz
2017 IEEE International Conference on Computer Vision Workshops (MBCC @ICCV 2017), 2017
H. Sattar, A. Bulling and M. Fritz
2017 IEEE International Conference on Computer Vision Workshops (MBCC @ICCV 2017), 2017
Abstract
Previous work focused on predicting visual search targets from human
fixations but, in the real world, a specific target is often not known, e.g.
when searching for a present for a friend. In this work we instead study the
problem of predicting the mental picture, i.e. only an abstract idea instead of
a specific target. This task is significantly more challenging given that
mental pictures of the same target category can vary widely depending on
personal biases, and given that characteristic target attributes can often not
be verbalised explicitly. We instead propose to use gaze information as
implicit information on users' mental picture and present a novel gaze pooling
layer to seamlessly integrate semantic and localized fixation information into
a deep image representation. We show that we can robustly predict both the
mental picture's category as well as attributes on a novel dataset containing
fixation data of 14 users searching for targets on a subset of the DeepFahion
dataset. Our results have important implications for future search interfaces
and suggest deep gaze pooling as a general-purpose approach for gaze-supported
computer vision systems.
MARCOnI -- ConvNet-Based MARker-Less Motion Capture in Outdoor and Indoor Scenes
A. Elhayek, E. de Aguiar, A. Jain, J. Tompson, L. Pishchulin, M. Andriluka, C. Bregler, B. Schiele and C. Theobalt
IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 39, Number 3, p.501–514,2017
A. Elhayek, E. de Aguiar, A. Jain, J. Tompson, L. Pishchulin, M. Andriluka, C. Bregler, B. Schiele and C. Theobalt
IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 39, Number 3, p.501–514,2017
A Compact Representation of Human Actions by Sliding Coordinate Coding
R. Ding, Q. Sun, M. Liu and H. Liu
International Journal of Advanced Robotic Systems, Volume 14, Number 6, 2017
R. Ding, Q. Sun, M. Liu and H. Liu
International Journal of Advanced Robotic Systems, Volume 14, Number 6, 2017
Movie Description
A. Rohrbach, A. Torabi, M. Rohrbach, N. Tandon, C. Pal, H. Larochelle, A. Courville and B. Schiele
International Journal of Computer Vision, Volume 123, Number 1, 2017
A. Rohrbach, A. Torabi, M. Rohrbach, N. Tandon, C. Pal, H. Larochelle, A. Courville and B. Schiele
International Journal of Computer Vision, Volume 123, Number 1, 2017
Abstract
Audio Description (AD) provides linguistic descriptions of movies and allows
visually impaired people to follow a movie along with their peers. Such
descriptions are by design mainly visual and thus naturally form an interesting
data source for computer vision and computational linguistics. In this work we
propose a novel dataset which contains transcribed ADs, which are temporally
aligned to full length movies. In addition we also collected and aligned movie
scripts used in prior work and compare the two sources of descriptions. In
total the Large Scale Movie Description Challenge (LSMDC) contains a parallel
corpus of 118,114 sentences and video clips from 202 movies. First we
characterize the dataset by benchmarking different approaches for generating
video descriptions. Comparing ADs to scripts, we find that ADs are indeed more
visual and describe precisely what is shown rather than what should happen
according to the scripts created prior to movie production. Furthermore, we
present and compare the results of several teams who participated in a
challenge organized in the context of the workshop "Describing and
Understanding Video & The Large Scale Movie Description Challenge (LSMDC)", at
ICCV 2015.
Look Together: Using Gaze for Assisting Co-located Collaborative Search
Y. Zhang, K. Pfeuffer, M. K. Chong, J. Alexander, A. Bulling and H. Gellersen
Personal and Ubiquitous Computing, Volume 21, Number 1, 2017
Y. Zhang, K. Pfeuffer, M. K. Chong, J. Alexander, A. Bulling and H. Gellersen
Personal and Ubiquitous Computing, Volume 21, Number 1, 2017
Analysis and Optimization of Graph Decompositions by Lifted Multicuts
A. Horňáková, J.-H. Lange and B. Andres
Proceedings of the 34th International Conference on Machine Learning (ICML 2017), 2017
A. Horňáková, J.-H. Lange and B. Andres
Proceedings of the 34th International Conference on Machine Learning (ICML 2017), 2017
Analysis and Improvement of the Visual Object Detection Pipeline
J. Hosang
PhD Thesis, Universität des Saarlandes, 2017
J. Hosang
PhD Thesis, Universität des Saarlandes, 2017
Abstract
Visual object detection has seen substantial improvements during the last years due to the possibilities enabled by deep learning. While research on image classification provides continuous progress on how to learn image representations and classifiers jointly, object detection research focuses on identifying how to properly use deep learning technology to effectively localise objects. In this thesis, we analyse and improve different aspects of the commonly used detection pipeline. We analyse ten years of research on pedestrian detection and find that improvement of feature representations was the driving factor. Motivated by this finding, we adapt an end-to-end learned detector architecture from general object detection to pedestrian detection. Our deep network outperforms all previous neural networks for pedestrian detection by a large margin, even without using additional training data. After substantial improvements on pedestrian detection in recent years, we investigate the gap between human performance and state-of-the-art pedestrian detectors. We find that pedestrian detectors still have a long way to go before they reach human performance, and we diagnose failure modes of several top performing detectors, giving direction to future research. As a side-effect we publish new, better localised annotations for the Caltech pedestrian benchmark. We analyse detection proposals as a preprocessing step for object detectors. We establish different metrics and compare a wide range of methods according to these metrics. By examining the relationship between localisation of proposals and final object detection performance, we define and experimentally verify a metric that can be used as a proxy for detector performance. Furthermore, we address a structural weakness of virtually all object detection pipelines: non-maximum suppression. We analyse why it is necessary and what the shortcomings of the most common approach are. To address these problems, we present work to overcome these shortcomings and to replace typical non-maximum suppression with a learnable alternative. The introduced paradigm paves the way to true end-to-end learning of object detectors without any post-processing. In summary, this thesis provides analyses of recent pedestrian detectors and detection proposals, improves pedestrian detection by employing deep neural networks, and presents a viable alternative to traditional non-maximum suppression.
Learning to Segment in Images and Videos with Different Forms of Supervision
A. Khoreva
PhD Thesis, Universität des Saarlandes, 2017
A. Khoreva
PhD Thesis, Universität des Saarlandes, 2017
Abstract
Much progress has been made in image and video segmentation<br>over the last years. To a large extent, the success can be attributed to<br>the strong appearance models completely learned from data, in particular<br>using deep learning methods. However,to perform best these methods require<br>large representative datasets for training with expensive pixel-level<br>annotations, which in case of videos are prohibitive to obtain. Therefore,<br>there is a need to relax this constraint and to consider alternative forms<br>of supervision, which are easier and cheaper to collect. In this thesis,<br>we aim to develop algorithms for learning to segment in images and videos<br>with different levels of supervision.<br>First, we develop approaches for training convolutional networks with weaker<br>forms of supervision, such as bounding boxes or image labels, for object<br>boundary estimation and semantic/instance labelling tasks. We propose to<br>generate pixel-level approximate groundtruth from these weaker forms of<br>annotations to train a network, which allows to achieve high-quality<br>results comparable to the full supervision quality without any<br>modifications of the network architecture or the training procedure.<br>Second, we address the problem of the excessive computational and memory<br>costs inherent to solving video segmentation via graphs. We propose<br>approaches to improve the runtime and memory efficiency as well as the<br>output segmentation quality by learning from the available training data<br>the best representation of the graph. In particular, we contribute with<br>learning must-link constraints, the topology and edge weights of the graph<br>as well as enhancing the graph nodes - superpixels - themselves.<br>Third, we tackle the task of pixel-level object tracking and address the<br>problem of the limited amount of densely annotated video data for training<br>convolutional networks. We introduce an architecture which allows training<br>with static images only and propose an elaborate data synthesis scheme<br>which creates a large number of training examples close to the target<br>domain from the given first frame mask. With the proposed techniques we<br>show that densely annotated consequent video data is not necessary to<br>achieve high-quality temporally coherent video segmentationresults.<br>In summary, this thesis advances the state of the art in weakly supervised<br>image segmentation, graph-based video segmentation and pixel-level object<br>tracking and contributes with the new ways of training convolutional<br>networks with a limited amount of pixel-level annotated training data.
Lucid Data Dreaming for Multiple Object Tracking
A. Khoreva, R. Benenson, E. Ilg, T. Brox and B. Schiele
Technical Report, 2017
(arXiv: 1703.09554) A. Khoreva, R. Benenson, E. Ilg, T. Brox and B. Schiele
Technical Report, 2017
Abstract
Convolutional networks reach top quality in pixel-level object tracking but
require a large amount of training data (1k ~ 10k) to deliver such results. We
propose a new training strategy which achieves state-of-the-art results across
three evaluation datasets while using 20x ~ 100x less annotated data than
competing methods. Instead of using large training sets hoping to generalize
across domains, we generate in-domain training data using the provided
annotation on the first frame of each video to synthesize ("lucid dream")
plausible future video frames. In-domain per-video training data allows us to
train high quality appearance- and motion-based models, as well as tune the
post-processing stage. This approach allows to reach competitive results even
when training from only a single annotated frame, without ImageNet
pre-training. Our results indicate that using a larger training set is not
automatically better, and that for the tracking task a smaller training set
that is closer to the target domain is more effective. This changes the mindset
regarding how many training samples and general "objectness" knowledge are
required for the object tracking task.
Image Classification with Limited Training Data and Class Ambiguity
M. Lapin
PhD Thesis, Universität des Saarlandes, 2017
M. Lapin
PhD Thesis, Universität des Saarlandes, 2017
Abstract
Modern image classification methods are based on supervised learning algorithms that require labeled training data. However, only a limited amount of annotated data may be available in certain applications due to scarcity of the data itself or high costs associated with human annotation. Introduction of additional information and structural constraints can help improve the performance of a learning algorithm. In this thesis, we study the framework of learning using privileged information and demonstrate its relation to learning with instance weights. We also consider multitask feature learning and develop an efficient dual optimization scheme that is particularly well suited to problems with high dimensional image descriptors. Scaling annotation to a large number of image categories leads to the problem of class ambiguity where clear distinction between the classes is no longer possible. Many real world images are naturally multilabel yet the existing annotation might only contain a single label. In this thesis, we propose and analyze a number of loss functions that allow for a certain tolerance in top k predictions of a learner. Our results indicate consistent improvements over the standard loss functions that put more penalty on the first incorrect prediction compared to the proposed losses. All proposed learning methods are complemented with efficient optimization schemes that are based on stochastic dual coordinate ascent for convex problems and on gradient descent for nonconvex formulations.
Acquiring Target Stacking Skills by Goal-Parameterized Deep Reinforcement Learning
W. Li, J. Bohg and M. Fritz
Technical Report, 2017
(arXiv: 1711.00267) W. Li, J. Bohg and M. Fritz
Technical Report, 2017
Abstract
Understanding physical phenomena is a key component of human intelligence and
enables physical interaction with previously unseen environments. In this
paper, we study how an artificial agent can autonomously acquire this intuition
through interaction with the environment. We created a synthetic block stacking
environment with physics simulation in which the agent can learn a policy
end-to-end through trial and error. Thereby, we bypass to explicitly model
physical knowledge within the policy. We are specifically interested in tasks
that require the agent to reach a given goal state that may be different for
every new trial. To this end, we propose a deep reinforcement learning
framework that learns policies which are parametrized by a goal. We validated
the model on a toy example navigating in a grid world with different target
positions and in a block stacking task with different target structures of the
final tower. In contrast to prior work, our policies show better generalization
across different goals.
Towards Holistic Machines: From Visual Recognition To Question Answering About Real-world Image
M. Malinowski
PhD Thesis, Universität des Saarlandes, 2017
M. Malinowski
PhD Thesis, Universität des Saarlandes, 2017
Abstract
Computer Vision has undergone major changes over the recent five years. Here, we investigate if the performance of such architectures generalizes to more complex tasks that require a more holistic approach to scene comprehension. The presented work focuses on learning spatial and multi-modal representations, and the foundations of a Visual Turing Test, where the scene understanding is tested by a series of questions about its content. In our studies, we propose DAQUAR, the first ‘question answering about real-world images’ dataset together with methods, termed a symbolic-based and a neural-based visual question answering architectures, that address the problem. The symbolic-based method relies on a semantic parser, a database of visual facts, and a bayesian formulation that accounts for various interpretations of the visual scene. The neural-based method is an end-to-end architecture composed of a question encoder, image encoder, multimodal embedding, and answer decoder. This architecture has proven to be effective in capturing language-based biases. It also becomes the standard component of other visual question answering architectures. Along with the methods, we also investigate various evaluation metrics that embraces uncertainty in word's meaning, and various interpretations of the scene and the question.
Person Recognition in Social Media Photos
S. J. Oh, R. Benenson, M. Fritz and B. Schiele
Technical Report, 2017
(arXiv: 1710.03224) S. J. Oh, R. Benenson, M. Fritz and B. Schiele
Technical Report, 2017
Abstract
People nowadays share large parts of their personal lives through social
media. Being able to automatically recognise people in personal photos may
greatly enhance user convenience by easing photo album organisation. For human
identification task, however, traditional focus of computer vision has been
face recognition and pedestrian re-identification. Person recognition in social
media photos sets new challenges for computer vision, including non-cooperative
subjects (e.g. backward viewpoints, unusual poses) and great changes in
appearance. To tackle this problem, we build a simple person recognition
framework that leverages convnet features from multiple image regions (head,
body, etc.). We propose new recognition scenarios that focus on the time and
appearance gap between training and testing samples. We present an in-depth
analysis of the importance of different features according to time and
viewpoint generalisability. In the process, we verify that our simple approach
achieves the state of the art result on the PIPA benchmark, arguably the
largest social media based benchmark for person recognition to date with
diverse poses, viewpoints, social groups, and events.
Compared the conference version of the paper, this paper additionally
presents (1) analysis of a face recogniser (DeepID2+), (2) new method naeil2
that combines the conference version method naeil and DeepID2+ to achieve state
of the art results even compared to post-conference works, (3) discussion of
related work since the conference version, (4) additional analysis including
the head viewpoint-wise breakdown of performance, and (5) results on the
open-world setup.
Whitening Black-Box Neural Networks
S. J. Oh, M. Augustin, B. Schiele and M. Fritz
Technical Report, 2017
(arXiv: 1711.01768) S. J. Oh, M. Augustin, B. Schiele and M. Fritz
Technical Report, 2017
Abstract
Many deployed learned models are black boxes: given input, returns output.
Internal information about the model, such as the architecture, optimisation
procedure, or training data, is not disclosed explicitly as it might contain
proprietary information or make the system more vulnerable. This work shows
that such attributes of neural networks can be exposed from a sequence of
queries. This has multiple implications. On the one hand, our work exposes the
vulnerability of black-box neural networks to different types of attacks -- we
show that the revealed internal information helps generate more effective
adversarial examples against the black box model. On the other hand, this
technique can be used for better protection of private content from automatic
recognition models using adversarial examples. Our paper suggests that it is
actually hard to draw a line between white box and black box models.
Attentive Explanations: Justifying Decisions and Pointing to the Evidence (Extended Abstract)
D. H. Park, L. A. Hendricks, Z. Akata, A. Rohrbach, B. Schiele, T. Darrell and M. Rohrbach
Technical Report, 2017
(arXiv: 1711.07373) D. H. Park, L. A. Hendricks, Z. Akata, A. Rohrbach, B. Schiele, T. Darrell and M. Rohrbach
Technical Report, 2017
Abstract
Deep models are the defacto standard in visual decision problems due to their<br>impressive performance on a wide array of visual tasks. On the other hand,<br>their opaqueness has led to a surge of interest in explainable systems. In this<br>work, we emphasize the importance of model explanation in various forms such as<br>visual pointing and textual justification. The lack of data with justification<br>annotations is one of the bottlenecks of generating multimodal explanations.<br>Thus, we propose two large-scale datasets with annotations that visually and<br>textually justify a classification decision for various activities, i.e. ACT-X,<br>and for question answering, i.e. VQA-X. We also introduce a multimodal<br>methodology for generating visual and textual explanations simultaneously. We<br>quantitatively show that training with the textual explanations not only yields<br>better textual justification models, but also models that better localize the<br>evidence that support their decision.<br>
Generation and Grounding of Natural Language Descriptions for Visual Data
A. Rohrbach
PhD Thesis, Universität des Saarlandes, 2017
A. Rohrbach
PhD Thesis, Universität des Saarlandes, 2017
Abstract
Generating natural language descriptions for visual data links computer vision and computational linguistics. Being able to generate a concise and human-readable description of a video is a step towards visual understanding. At the same time, grounding natural language in visual data provides disambiguation for the linguistic concepts, necessary for many applications. This thesis focuses on both directions and tackles three specific problems. First, we develop recognition approaches to understand video of complex cooking activities. We propose an approach to generate coherent multi-sentence descriptions for our videos. Furthermore, we tackle the new task of describing videos at variable level of detail. Second, we present a large-scale dataset of movies and aligned professional descriptions. We propose an approach, which learns from videos and sentences to describe movie clips relying on robust recognition of visual semantic concepts. Third, we propose an approach to ground textual phrases in images with little or no localization supervision, which we further improve by introducing Multimodal Compact Bilinear Pooling for combining language and vision representations. Finally, we jointly address the task of describing videos and grounding the described people. To summarize, this thesis advances the state-of-the-art in automatic video description and visual grounding and also contributes large datasets for studying the intersection of computer vision and computational linguistics.
Visual Decoding of Targets During Visual Search From Human Eye Fixations
H. Sattar, M. Fritz and A. Bulling
Technical Report, 2017
(arXiv: 1706.05993) H. Sattar, M. Fritz and A. Bulling
Technical Report, 2017
Abstract
What does human gaze reveal about a users' intents and to which extend can
these intents be inferred or even visualized? Gaze was proposed as an implicit
source of information to predict the target of visual search and, more
recently, to predict the object class and attributes of the search target. In
this work, we go one step further and investigate the feasibility of combining
recent advances in encoding human gaze information using deep convolutional
neural networks with the power of generative image models to visually decode,
i.e. create a visual representation of, the search target. Such visual decoding
is challenging for two reasons: 1) the search target only resides in the user's
mind as a subjective visual pattern, and can most often not even be described
verbally by the person, and 2) it is, as of yet, unclear if gaze fixations
contain sufficient information for this task at all. We show, for the first
time, that visual representations of search targets can indeed be decoded only
from human gaze fixations. We propose to first encode fixations into a semantic
representation and then decode this representation into an image. We evaluate
our method on a recent gaze dataset of 14 participants searching for clothing
in image collages and validate the model's predictions using two human studies.
Our results show that 62% (Chance level = 10%) of the time users were able to
select the categories of the decoded image right. In our second studies we show
the importance of a local gaze encoding for decoding visual search targets of
user
People detection and tracking in crowded scenes
S. Tang
PhD Thesis, Universität des Saarlandes, 2017
S. Tang
PhD Thesis, Universität des Saarlandes, 2017
Abstract
People are often a central element of visual scenes, particularly in real-world street scenes. Thus it has been a long-standing goal in Computer Vision to develop methods aiming at analyzing humans in visual data. Due to the complexity of real-world scenes, visual understanding of people remains challenging for machine perception. In this thesis we focus on advancing the techniques for people detection and tracking in crowded street scenes. We also propose new models for human pose estimation and motion segmentation in realistic images and videos. First, we propose detection models that are jointly trained to detect single person as well as pairs of people under varying degrees of occlusion. The learning algorithm of our joint detector facilitates a tight integration of tracking and detection, because it is designed to address common failure cases during tracking due to long-term inter-object occlusions. Second, we propose novel multi person tracking models that formulate tracking as a graph partitioning problem. Our models jointly cluster detection hypotheses in space and time, eliminating the need for a heuristic non-maximum suppression. Furthermore, for crowded scenes, our tracking model encodes long-range person re-identification information into the detection clustering process in a unified and rigorous manner. Third, we explore the visual tracking task in different granularity. We present a tracking model that simultaneously clusters object bounding boxes and pixel level trajectories over time. This approach provides a rich understanding of the motion of objects in the scene. Last, we extend our tracking model for the multi person pose estimation task. We introduce a joint subset partitioning and labelling model where we simultaneously estimate the poses of all the people in the scene. In summary, this thesis addresses a number of diverse tasks that aim to enable vision systems to analyze people in realistic images and videos. In particular, the thesis proposes several novel ideas and rigorous mathematical formulations, pushes the boundary of state-of-the-arts and results in superior performance.
2016
Weakly Supervised Object Boundaries
A. Khoreva, R. Benenson, M. Omran, M. Hein and B. Schiele
29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), 2016
A. Khoreva, R. Benenson, M. Omran, M. Hein and B. Schiele
29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), 2016
Abstract
State-of-the-art learning based boundary detection methods require extensive
training data. Since labelling object boundaries is one of the most expensive
types of annotations, there is a need to relax the requirement to carefully
annotate images to make both the training more affordable and to extend the
amount of training data. In this paper we propose a technique to generate
weakly supervised annotations and show that bounding box annotations alone
suffice to reach high-quality object boundaries without using any
object-specific boundary annotations. With the proposed weak supervision
techniques we achieve the top performance on the object boundary detection
task, outperforming by a large margin the current fully supervised
state-of-the-art methods.
Deep Reflectance Maps
K. Rematas, T. Ritschel, M. Fritz, E. Gavves and T. Tuytelaars
29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), 2016
K. Rematas, T. Ritschel, M. Fritz, E. Gavves and T. Tuytelaars
29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), 2016
Abstract
Undoing the image formation process and therefore decomposing appearance into
its intrinsic properties is a challenging task due to the under-constraint
nature of this inverse problem. While significant progress has been made on
inferring shape, materials and illumination from images only, progress in an
unconstrained setting is still limited. We propose a convolutional neural
architecture to estimate reflectance maps of specular materials in natural
lighting conditions. We achieve this in an end-to-end learning formulation that
directly predicts a reflectance map from the image itself. We show how to
improve estimates by facilitating additional supervision in an indirect scheme
that first predicts surface orientation and afterwards predicts the reflectance
map by a learning-based sparse data interpolation.
In order to analyze performance on this difficult task, we propose a new
challenge of Specular MAterials on SHapes with complex IllumiNation (SMASHINg)
using both synthetic and real images. Furthermore, we show the application of
our method to a range of image-based editing tasks on real images.
Learning What and Where to Draw
S. Reed, Z. Akata, S. Mohan, S. Tenka, B. Schiele and L. Honglak
Advances in Neural Information Processing Systems 29 (NIPS 2016), 2016
S. Reed, Z. Akata, S. Mohan, S. Tenka, B. Schiele and L. Honglak
Advances in Neural Information Processing Systems 29 (NIPS 2016), 2016
On the Verge: Voluntary Convergences for Accurate and Precise Timing of Gaze Input
D. Kirst and A. Bulling
CHI 2016 Extended Abstracts, 2016
D. Kirst and A. Bulling
CHI 2016 Extended Abstracts, 2016
Abstract
Rotations performed with the index finger and thumb involve some of the most complex motor action among common multi-touch gestures, yet little is known about the factors affecting performance and ergonomics. This note presents results from a study where the angle, direction, diameter, and position of rotations were systematically manipulated. Subjects were asked to perform the rotations as quickly as possible without losing contact with the display, and were allowed to skip rotations that were too uncomfortable. The data show surprising interaction effects among the variables, and help us identify whole categories of rotations that are slow and cumbersome for users.
Generating Visual Explanations
L. A. Hendricks, Z. Akata, M. Rohrbach, J. Donahue, B. Schiele and T. Darrell
Computer Vision -- ECCV 2016, 2016
L. A. Hendricks, Z. Akata, M. Rohrbach, J. Donahue, B. Schiele and T. Darrell
Computer Vision -- ECCV 2016, 2016
Abstract
Clearly explaining a rationale for a classification decision to an end-user
can be as important as the decision itself. Existing approaches for deep visual
recognition are generally opaque and do not output any justification text;
contemporary vision-language models can describe image content but fail to take
into account class-discriminative image aspects which justify visual
predictions. We propose a new model that focuses on the discriminating
properties of the visible object, jointly predicts a class label, and explains
why the predicted label is appropriate for the image. We propose a novel loss
function based on sampling and reinforcement learning that learns to generate
sentences that realize a global sentence property, such as class specificity.
Our results on a fine-grained bird species classification dataset show that our
model is able to generate explanations which are not only consistent with an
image but also more discriminative than descriptions produced by existing
captioning methods.
DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model
E. Insafutdinov, L. Pishchulin, B. Andres, M. Andriluka and B. Schiele
Computer Vision -- ECCV 2016, 2016
E. Insafutdinov, L. Pishchulin, B. Andres, M. Andriluka and B. Schiele
Computer Vision -- ECCV 2016, 2016
Abstract
The goal of this paper is to advance the state-of-the-art of articulated pose
estimation in scenes with multiple people. To that end we contribute on three
fronts. We propose (1) improved body part detectors that generate effective
bottom-up proposals for body parts; (2) novel image-conditioned pairwise terms
that allow to assemble the proposals into a variable number of consistent body
part configurations; and (3) an incremental optimization strategy that explores
the search space more efficiently thus leading both to better performance and
significant speed-up factors. We evaluate our approach on two single-person and
two multi-person pose estimation benchmarks. The proposed approach
significantly outperforms best known multi-person pose estimation results while
demonstrating competitive performance on the task of single person pose
estimation. Models and code available at http://pose.mpi-inf.mpg.de
VConv-DAE: Deep Volumetric Shape Learning Without Object Labels
A. Sharma, O. Grau and M. Fritz
Computer Vision - ECCV 2016 Workshops, 2016
A. Sharma, O. Grau and M. Fritz
Computer Vision - ECCV 2016 Workshops, 2016
Abstract
With the advent of affordable depth sensors, 3D capture becomes more and more
ubiquitous and already has made its way into commercial products. Yet,
capturing the geometry or complete shapes of everyday objects using scanning
devices (eg. Kinect) still comes with several challenges that result in noise
or even incomplete shapes. Recent success in deep learning has shown how to
learn complex shape distributions in a data-driven way from large scale 3D CAD
Model collections and to utilize them for 3D processing on volumetric
representations and thereby circumventing problems of topology and
tessellation. Prior work has shown encouraging results on problems ranging from
shape completion to recognition. We provide an analysis of such approaches and
discover that training as well as the resulting representation are strongly and
unnecessarily tied to the notion of object labels. Furthermore, deep learning
research argues ~\cite{Vincent08} that learning representation with
over-complete model are more prone to overfitting compared to the approach that
learns from noisy data. Thus, we investigate a full convolutional volumetric
denoising auto encoder that is trained in a unsupervised fashion. It
outperforms prior work on recognition as well as more challenging tasks like
denoising and shape completion. In addition, our approach is atleast two order
of magnitude faster at test time and thus, provides a path to scaling up 3D
deep learning.
Improved Image Boundaries for Better Video Segmentation
A. Khoreva, R. Benenson, F. Galasso, M. Hein and B. Schiele
Computer Vision -- ECCV 2016 Workshops, 2016
A. Khoreva, R. Benenson, F. Galasso, M. Hein and B. Schiele
Computer Vision -- ECCV 2016 Workshops, 2016
Abstract
Graph-based video segmentation methods rely on superpixels as starting point.
While most previous work has focused on the construction of the graph edges and
weights as well as solving the graph partitioning problem, this paper focuses
on better superpixels for video segmentation. We demonstrate by a comparative
analysis that superpixels extracted from boundaries perform best, and show that
boundary estimation can be significantly improved via image and time domain
cues. With superpixels generated from our better boundaries we observe
consistent improvement for two video segmentation methods in two different
datasets.
Eyewear Computing -- Augmenting the Human with Head-mounted Wearable Assistants
A. Bulling, O. Cakmakci, K. Kunze and J. M. Rehg (Eds.)
Schloss Dagstuhl, 2016
A. Bulling, O. Cakmakci, K. Kunze and J. M. Rehg (Eds.)
Schloss Dagstuhl, 2016
Ask Your Neurons Again: Analysis of Deep Methods with Global Image Representation
M. Malinowski, M. Rohrbach and M. Fritz
IEEE Conference on Computer Vision and Pattern Recognition Workshops (VQA 2016), 2016
(Accepted/in press) M. Malinowski, M. Rohrbach and M. Fritz
IEEE Conference on Computer Vision and Pattern Recognition Workshops (VQA 2016), 2016
Abstract
We are addressing an open-ended question answering task
about real-world images. With the help of currently available methods
developed in Computer Vision and Natural Language Processing, we would
like to push an architecture with a global visual representation to its
limits. In our contribution, we show how to achieve competitive
performance on VQA with global visual features (Residual Net) together
with a carefully desgined architecture.
Long Term Boundary Extrapolation for Deterministic Motion
A. Bhattacharyya, M. Malinowski and M. Fritz
NIPS Workshop on Intuitive Physics, 2016
A. Bhattacharyya, M. Malinowski and M. Fritz
NIPS Workshop on Intuitive Physics, 2016
A Convnet for Non-maximum Suppression
J. Hosang, R. Benenson and B. Schiele
Pattern Recognition (GCPR 2016), 2016
J. Hosang, R. Benenson and B. Schiele
Pattern Recognition (GCPR 2016), 2016
Abstract
Non-maximum suppression (NMS) is used in virtually all state-of-the-art
object detection pipelines. While essential object detection ingredients such
as features, classifiers, and proposal methods have been extensively researched
surprisingly little work has aimed to systematically address NMS. The de-facto
standard for NMS is based on greedy clustering with a fixed distance threshold,
which forces to trade-off recall versus precision. We propose a convnet
designed to perform NMS of a given set of detections. We report experiments on
a synthetic setup, and results on crowded pedestrian detection scenes. Our
approach overcomes the intrinsic limitations of greedy NMS, obtaining better
recall and precision.
Generative Adversarial Text to Image Synthesis
S. Reed, Z. Akata, X. Yan, L. Logeswaran, B. Schiele and H. Lee
Proceedings of the 33rd International Conference on Machine Learning (ICML 2016), 2016
S. Reed, Z. Akata, X. Yan, L. Logeswaran, B. Schiele and H. Lee
Proceedings of the 33rd International Conference on Machine Learning (ICML 2016), 2016
Mean Box Pooling: A Rich Image Representation and Output Embedding for the Visual Madlibs Task
A. Mokarian Forooshani, M. Malinowski and M. Fritz
Proceedings of the British Machine Vision Conference (BMVC 2016), 2016
A. Mokarian Forooshani, M. Malinowski and M. Fritz
Proceedings of the British Machine Vision Conference (BMVC 2016), 2016
Commonsense in Parts: Mining Part-Whole Relations from the Web and Image Tags
N. Tandon, C. D. Hariman, J. Urbani, A. Rohrbach, M. Rohrbach and G. Weikum
Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, 2016
N. Tandon, C. D. Hariman, J. Urbani, A. Rohrbach, M. Rohrbach and G. Weikum
Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, 2016
Spatio-Temporal Image Boundary Extrapolation
A. Bhattacharyya, M. Malinowski and M. Fritz
Technical Report, 2016
(arXiv: 1605.07363) A. Bhattacharyya, M. Malinowski and M. Fritz
Technical Report, 2016
Abstract
Boundary prediction in images as well as video has been a very active topic
of research and organizing visual information into boundaries and segments is
believed to be a corner stone of visual perception. While prior work has
focused on predicting boundaries for observed frames, our work aims at
predicting boundaries of future unobserved frames. This requires our model to
learn about the fate of boundaries and extrapolate motion patterns. We
experiment on established real-world video segmentation dataset, which provides
a testbed for this new task. We show for the first time spatio-temporal
boundary extrapolation in this challenging scenario. Furthermore, we show
long-term prediction of boundaries in situations where the motion is governed
by the laws of physics. We successfully predict boundaries in a billiard
scenario without any assumptions of a strong parametric model or any object
notion. We argue that our model has with minimalistic model assumptions derived
a notion of 'intuitive physics' that can be applied to novel scenes.
Bayesian Non-Parametrics for Multi-Modal Segmentation
W.-C. Chiu
PhD Thesis, Universität des Saarlandes, 2016
W.-C. Chiu
PhD Thesis, Universität des Saarlandes, 2016
Natural Illumination from Multiple Materials Using Deep Learning
S. Georgoulis, K. Rematas, T. Ritschel, M. Fritz, T. Tuytelaars and L. Van Gool
Technical Report, 2016
(arXiv: 1611.09325) S. Georgoulis, K. Rematas, T. Ritschel, M. Fritz, T. Tuytelaars and L. Van Gool
Technical Report, 2016
Abstract
Recovering natural illumination from a single Low-Dynamic Range (LDR) image
is a challenging task. To remedy this situation we exploit two properties often
found in everyday images. First, images rarely show a single material, but
rather multiple ones that all reflect the same illumination. However, the
appearance of each material is observed only for some surface orientations, not
all. Second, parts of the illumination are often directly observed in the
background, without being affected by reflection. Typically, this directly
observed part of the illumination is even smaller. We propose a deep
Convolutional Neural Network (CNN) that combines prior knowledge about the
statistics of illumination and reflectance with an input that makes explicit
use of these two observations. Our approach maps multiple partial LDR material
observations represented as reflectance maps and a background image to a
spherical High-Dynamic Range (HDR) illumination map. For training and testing
we propose a new data set comprising of synthetic and real images with multiple
materials observed under the same illumination. Qualitative and quantitative
evidence shows how both multi-material and using a background are essential to
improve illumination estimations.
DeLight-Net: Decomposing Reflectance Maps into Specular Materials and Natural Illumination
S. Georgoulis, K. Rematas, T. Ritschel, M. Fritz, L. Van Gool and T. Tuytelaars
Technical Report, 2016
(arXiv: 1603.08240) S. Georgoulis, K. Rematas, T. Ritschel, M. Fritz, L. Van Gool and T. Tuytelaars
Technical Report, 2016
Abstract
In this paper we are extracting surface reflectance and natural environmental
illumination from a reflectance map, i.e. from a single 2D image of a sphere of
one material under one illumination. This is a notoriously difficult problem,
yet key to various re-rendering applications. With the recent advances in
estimating reflectance maps from 2D images their further decomposition has
become increasingly relevant.
To this end, we propose a Convolutional Neural Network (CNN) architecture to
reconstruct both material parameters (i.e. Phong) as well as illumination (i.e.
high-resolution spherical illumination maps), that is solely trained on
synthetic data. We demonstrate that decomposition of synthetic as well as real
photographs of reflectance maps, both in High Dynamic Range (HDR), and, for the
first time, on Low Dynamic Range (LDR) as well. Results are compared to
previous approaches quantitatively as well as qualitatively in terms of
re-renderings where illumination, material, view or shape are changed.
RGBD Semantic Segmentation Using Spatio-Temporal Data-Driven Pooling
Y. He, W.-C. Chiu, M. Keuper and M. Fritz
Technical Report, 2016
(arXiv: 1604.02388) Y. He, W.-C. Chiu, M. Keuper and M. Fritz
Technical Report, 2016
Abstract
Beyond the success in classification, neural networks have recently shown
strong results on pixel-wise prediction tasks like image semantic segmentation
on RGBD data. However, the commonly used deconvolutional layers for upsampling
intermediate representations to the full-resolution output still show different
failure modes, like imprecise segmentation boundaries and label mistakes in
particular on large, weakly textured objects (e.g. fridge, whiteboard, door).
We attribute these errors in part to the rigid way, current network aggregate
information, that can be either too local (missing context) or too global
(inaccurate boundaries). Therefore we propose a data-driven pooling layer that
integrates with fully convolutional architectures and utilizes boundary
detection from RGBD image segmentation approaches. We extend our approach to
leverage region-level correspondences across images with an additional temporal
pooling stage. We evaluate our approach on the NYU-Depth-V2 dataset comprised
of indoor RGBD video sequences and compare it to various state-of-the-art
baselines. Besides a general improvement over the state-of-the-art, our
approach shows particularly good results in terms of accuracy of the predicted
boundaries and in segmenting previously problematic classes.
End-to-End Eye Movement Detection Using Convolutional Neural Networks
S. Hoppe and A. Bulling
Technical Report, 2016
(arXiv: 1609.02452) S. Hoppe and A. Bulling
Technical Report, 2016
Abstract
Common computational methods for automated eye movement detection - i.e. the
task of detecting different types of eye movement in a continuous stream of
gaze data - are limited in that they either involve thresholding on
hand-crafted signal features, require individual detectors each only detecting
a single movement, or require pre-segmented data. We propose a novel approach
for eye movement detection that only involves learning a single detector
end-to-end, i.e. directly from the continuous gaze data stream and
simultaneously for different eye movements without any manual feature crafting
or segmentation. Our method is based on convolutional neural networks (CNN)
that recently demonstrated superior performance in a variety of tasks in
computer vision, signal processing, and machine learning. We further introduce
a novel multi-participant dataset that contains scripted and free-viewing
sequences of ground-truth annotated saccades, fixations, and smooth pursuits.
We show that our CNN-based method outperforms state-of-the-art baselines by a
large margin on this challenging dataset, thereby underlining the significant
potential of this approach for holistic, robust, and accurate eye movement
protocol analysis.
A Multi-cut Formulation for Joint Segmentation and Tracking of Multiple Objects
M. Keuper, S. Tang, Z. Yu, B. Andres, T. Brox and B. Schiele
Technical Report, 2016
(arXiv: 1607.06317) M. Keuper, S. Tang, Z. Yu, B. Andres, T. Brox and B. Schiele
Technical Report, 2016
Abstract
Recently, Minimum Cost Multicut Formulations have been proposed and proven to
be successful in both motion trajectory segmentation and multi-target tracking
scenarios. Both tasks benefit from decomposing a graphical model into an
optimal number of connected components based on attractive and repulsive
pairwise terms. The two tasks are formulated on different levels of granularity
and, accordingly, leverage mostly local information for motion segmentation and
mostly high-level information for multi-target tracking. In this paper we argue
that point trajectories and their local relationships can contribute to the
high-level task of multi-target tracking and also argue that high-level cues
from object detection and tracking are helpful to solve motion segmentation. We
propose a joint graphical model for point trajectories and object detections
whose Multicuts are solutions to motion segmentation {\it and} multi-target
tracking problems at once. Results on the FBMS59 motion segmentation benchmark
as well as on pedestrian tracking sequences from the 2D MOT 2015 benchmark
demonstrate the promise of this joint approach.
To Fall Or Not To Fall: A Visual Approach to Physical Stability Prediction
W. Li, S. Azimi, A. Leonardis and M. Fritz
Technical Report, 2016
(arXiv: 1604.00066) W. Li, S. Azimi, A. Leonardis and M. Fritz
Technical Report, 2016
Abstract
Understanding physical phenomena is a key competence that enables humans and
animals to act and interact under uncertain perception in previously unseen
environments containing novel object and their configurations. Developmental
psychology has shown that such skills are acquired by infants from observations
at a very early stage.
In this paper, we contrast a more traditional approach of taking a
model-based route with explicit 3D representations and physical simulation by
an end-to-end approach that directly predicts stability and related quantities
from appearance. We ask the question if and to what extent and quality such a
skill can directly be acquired in a data-driven way bypassing the need for an
explicit simulation.
We present a learning-based approach based on simulated data that predicts
stability of towers comprised of wooden blocks under different conditions and
quantities related to the potential fall of the towers. The evaluation is
carried out on synthetic data and compared to human judgments on the same
stimuli.
Tutorial on Answering Questions about Images with Deep Learning
M. Malinowski and M. Fritz
Technical Report, 2016
(arXiv: 1610.01076) M. Malinowski and M. Fritz
Technical Report, 2016
Abstract
Together with the development of more accurate methods in Computer Vision and
Natural Language Understanding, holistic architectures that answer on questions
about the content of real-world images have emerged. In this tutorial, we build
a neural-based approach to answer questions about images. We base our tutorial
on two datasets: (mostly on) DAQUAR, and (a bit on) VQA. With small tweaks the
models that we present here can achieve a competitive performance on both
datasets, in fact, they are among the best methods that use a combination of
LSTM with a global, full frame CNN representation of an image. We hope that
after reading this tutorial, the reader will be able to use Deep Learning
frameworks, such as Keras and introduced Kraino, to build various architectures
that will lead to a further performance improvement on this challenging task.
Attentive Explanations: Justifying Decisions and Pointing to the Evidence
D. H. Park, L. A. Hendricks, Z. Akata, B. Schiele, T. Darrell and M. Rohrbach
Technical Report, 2016
(arXiv: 1612.04757) D. H. Park, L. A. Hendricks, Z. Akata, B. Schiele, T. Darrell and M. Rohrbach
Technical Report, 2016
Abstract
Deep models are the defacto standard in visual decision models due to their<br>impressive performance on a wide array of visual tasks. However, they are<br>frequently seen as opaque and are unable to explain their decisions. In<br>contrast, humans can justify their decisions with natural language and point to<br>the evidence in the visual world which led to their decisions. We postulate<br>that deep models can do this as well and propose our Pointing and Justification<br>(PJ-X) model which can justify its decision with a sentence and point to the<br>evidence by introspecting its decision and explanation process using an<br>attention mechanism. Unfortunately there is no dataset available with reference<br>explanations for visual decision making. We thus collect two datasets in two<br>domains where it is interesting and challenging to explain decisions. First, we<br>extend the visual question answering task to not only provide an answer but<br>also a natural language explanation for the answer. Second, we focus on<br>explaining human activities which is traditionally more challenging than object<br>classification. We extensively evaluate our PJ-X model, both on the<br>justification and pointing tasks, by comparing it to prior models and ablations<br>using both automatic and human evaluations.<br>
Articulated People Detection and Pose Estimation in Challenging Real World Environments
L. Pishchulin
PhD Thesis, Universität des Saarlandes, 2016
L. Pishchulin
PhD Thesis, Universität des Saarlandes, 2016
EgoCap: Egocentric Marker-less Motion Capture with Two Fisheye Cameras (Extended Abstract)
H. Rhodin, C. Richardt, D. Casas, E. Insafutdinov, M. Shafiei, H.-P. Seidel, B. Schiele and C. Theobalt
Technical Report, 2016b
(arXiv: 1701.00142) H. Rhodin, C. Richardt, D. Casas, E. Insafutdinov, M. Shafiei, H.-P. Seidel, B. Schiele and C. Theobalt
Technical Report, 2016b
Abstract
Marker-based and marker-less optical skeletal motion-capture methods use an
outside-in arrangement of cameras placed around a scene, with viewpoints
converging on the center. They often create discomfort by possibly needed
marker suits, and their recording volume is severely restricted and often
constrained to indoor scenes with controlled backgrounds. We therefore propose
a new method for real-time, marker-less and egocentric motion capture which
estimates the full-body skeleton pose from a lightweight stereo pair of fisheye
cameras that are attached to a helmet or virtual-reality headset. It combines
the strength of a new generative pose estimation framework for fisheye views
with a ConvNet-based body-part detector trained on a new automatically
annotated and augmented dataset. Our inside-in method captures full-body motion
in general indoor and outdoor scenes, and also crowded scenes.
Seeing with Humans: Gaze-Assisted Neural Image Captioning
Y. Sugano and A. Bulling
Technical Report, 2016
(arXiv: 1608.05203) Y. Sugano and A. Bulling
Technical Report, 2016
Abstract
Gaze reflects how humans process visual scenes and is therefore increasingly
used in computer vision systems. Previous works demonstrated the potential of
gaze for object-centric tasks, such as object localization and recognition, but
it remains unclear if gaze can also be beneficial for scene-centric tasks, such
as image captioning. We present a new perspective on gaze-assisted image
captioning by studying the interplay between human gaze and the attention
mechanism of deep neural networks. Using a public large-scale gaze dataset, we
first assess the relationship between state-of-the-art object and scene
recognition models, bottom-up visual saliency, and human gaze. We then propose
a novel split attention model for image captioning. Our model integrates human
gaze information into an attention-based long short-term memory architecture,
and allows the algorithm to allocate attention selectively to both fixated and
non-fixated image regions. Through evaluation on the COCO/SALICON datasets we
show that our method improves image captioning performance and that gaze can
complement machine attention for semantic scene understanding tasks.
2015
On the Interplay between Spontaneous Spoken Instructions and Human Visual Behaviour in an Indoor Guidance Task
N. Koleva, S. Hoppe, M. M. Moniri, M. Staudte and A. Bulling
37th Annual Meeting of the Cognitive Science Society (COGSCI 2015), 2015
N. Koleva, S. Hoppe, M. M. Moniri, M. Staudte and A. Bulling
37th Annual Meeting of the Cognitive Science Society (COGSCI 2015), 2015
Efficient Output Kernel Learning for Multiple Tasks
P. Jawanpuria, M. Lapin, M. Hein and B. Schiele
Advances in Neural Information Processing Systems 28 (NIPS 2015), 2015
P. Jawanpuria, M. Lapin, M. Hein and B. Schiele
Advances in Neural Information Processing Systems 28 (NIPS 2015), 2015
Top-k Multiclass SVM
M. Lapin, M. Hein and B. Schiele
Advances in Neural Information Processing Systems 28 (NIPS 2015), 2015
M. Lapin, M. Hein and B. Schiele
Advances in Neural Information Processing Systems 28 (NIPS 2015), 2015
Rekonstruktion zerebraler Gefässnetzwerke aus in-vivo μMRA mittels physiologischem Vorwissen zur lokalen Gefässgeometrie
M. Rempfler, M. Schneider, G. D. Ielacqua, T. Sprenger, X. Xiao, S. R. Stock, J. Klohs, G. Székely, B. Andres and B. H. Menze
Bildverarbeitung für die Medizin 2015 (BVM 2015), 2015
M. Rempfler, M. Schneider, G. D. Ielacqua, T. Sprenger, X. Xiao, S. R. Stock, J. Klohs, G. Székely, B. Andres and B. H. Menze
Bildverarbeitung für die Medizin 2015 (BVM 2015), 2015
A Study on the Natural History of Scanning Behaviour in Patients with Visual Field Defects after Stroke
T. Loetscher, C. Chen, S. Wignall, A. Bulling, S. Hoppe, O. Churches, N. A. Thomas, M. E. R. Nicholls and A. Lee
BMC Neurology, Volume 15, 2015
T. Loetscher, C. Chen, S. Wignall, A. Bulling, S. Hoppe, O. Churches, N. A. Thomas, M. E. R. Nicholls and A. Lee
BMC Neurology, Volume 15, 2015
The Royal Corgi: Exploring Social Gaze Interaction for Immersive Gameplay
M. Vidal, R. Bismuth, A. Bulling and H. Gellersen
CHI 2015, 33rd Annual ACM Conference on Human Factors in Computing Systems, 2015
M. Vidal, R. Bismuth, A. Bulling and H. Gellersen
CHI 2015, 33rd Annual ACM Conference on Human Factors in Computing Systems, 2015
Abstract
The eyes are a rich channel for non-verbal communication in
our daily interactions. We propose social gaze interaction as a game
mechanic to enhance user interactions with virtual characters. We
develop a game from the ground-up in which characters are esigned to be
reactive to the player’s gaze in social ways, such as etting annoyed
when the player seems distracted or changing their dialogue depending on
the player’s apparent focus of ttention. Results from a qualitative user
study provide insights bout how social gaze interaction is intuitive for
users, elicits deep feelings of immersion, and highlight the players’
self-consciousness of their own eye movements through their strong
reactions to the characters
Computational Modelling and Prediction of Gaze Estimation Error for Head-mounted Eye Trackers
M. Barz, A. Bulling and F. Daiber
Technical Report, 2015
M. Barz, A. Bulling and F. Daiber
Technical Report, 2015
Abstract
Head-mounted eye tracking has significant potential for
mobile gaze-based interaction with ambient displays but current
interfaces lack information about the tracker\'s gaze estimation error.
Consequently, current interfaces do not exploit the full potential of
gaze input as the inherent estimation error can not be dealt with. The
error depends on the physical properties of the display and constantly
varies with changes in position and distance of the user to the display.
In this work we present a computational model of gaze estimation error
for head-mounted eye trackers. Our model covers the full processing
pipeline for mobile gaze estimation, namely mapping of pupil positions
to scene camera coordinates, marker-based display detection, and display
mapping. We build the model based on a series of controlled measurements
of a sample state-of-the-art monocular head-mounted eye tracker. Results
show that our model can predict gaze estimation error with a root mean
squared error of 17.99~px ($1.96^\\circ$).
GazeProjector: Location-independent Gaze Interaction on and Across Multiple Displays
C. Lander, S. Gehring, A. Krüger, S. Boring and A. Bulling
Technical Report, 2015
C. Lander, S. Gehring, A. Krüger, S. Boring and A. Bulling
Technical Report, 2015
Abstract
Mobile gaze-based interaction with multiple displays may
occur from arbitrary positions and orientations. However, maintaining
high gaze estimation accuracy still represents a significant challenge.
To address this, we present GazeProjector, a system that combines
accurate point-of-gaze estimation with natural feature tracking on
displays to determine the mobile eye tracker’s position relative to a
display. The detected eye positions are transformed onto that display
allowing for gaze-based interaction. This allows for seamless gaze
estimation and interaction on (1) multiple displays of arbitrary sizes,
(2) independently of the user’s position and orientation to the display.
In a user study with 12 participants we compared GazeProjector to
existing well- established methods such as visual on-screen markers and
a state-of-the-art motion capture system. Our results show that our
approach is robust to varying head poses, orientations, and distances to
the display, while still providing high gaze estimation accuracy across
multiple displays without re-calibration. The system represents an
important step towards the vision of pervasive gaze-based interfaces.
See the Difference: Direct Pre-Image Reconstruction and Pose Estimation by Differentiating HOG
W.-C. Chiu and M. Fritz
ICCV 2015, IEEE International Conference on Computer Vision, 2015
W.-C. Chiu and M. Fritz
ICCV 2015, IEEE International Conference on Computer Vision, 2015
Ask Your Neurons: A Neural-based Approach to Answering Questions About Images
M. Malinowski, M. Rohrbach and M. Fritz
ICCV 2015, IEEE International Conference on Computer Vision, 2015
M. Malinowski, M. Rohrbach and M. Fritz
ICCV 2015, IEEE International Conference on Computer Vision, 2015
Rendering of Eyes for Eye-Shape Registration and Gaze Estimation
E. Wood, T. Baltrusaitis, X. Zhang, Y. Sugano, P. Robinson and A. Bulling
ICCV 2015, IEEE International Conference on Computer Vision, 2015
E. Wood, T. Baltrusaitis, X. Zhang, Y. Sugano, P. Robinson and A. Bulling
ICCV 2015, IEEE International Conference on Computer Vision, 2015
Efficient ConvNet-based Marker-less Motion Capture in General Scenes with a Low Number of Cameras
A. Elhayek, E. de Aguiar, J. Tompson, A. Jain, L. Pishchulin, M. Andriluka, C. Bregler, B. Schiele and C. Theobalt
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015), 2015
A. Elhayek, E. de Aguiar, J. Tompson, A. Jain, L. Pishchulin, M. Andriluka, C. Bregler, B. Schiele and C. Theobalt
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015), 2015
A Comparative Study of Modern Inference Techniques for Structured Discrete Energy Minimization Problems
J. H. Kappes, B. Andres, F. A. Hamprecht, C. Schnörr, S. Nowozin, D. Batra, S. Kim, B. X. Kausler, T. Kröger, J. Lellmann, N. Komodakis, B. Savchynskyy and C. Rother
International Journal of Computer Vision, Volume 115, Number 2, 2015
J. H. Kappes, B. Andres, F. A. Hamprecht, C. Schnörr, S. Nowozin, D. Batra, S. Kim, B. X. Kausler, T. Kröger, J. Lellmann, N. Komodakis, B. Savchynskyy and C. Rother
International Journal of Computer Vision, Volume 115, Number 2, 2015
Abstract
Szeliski et al. published an influential study in 2006 on energy minimization
methods for Markov Random Fields (MRF). This study provided valuable insights
in choosing the best optimization technique for certain classes of problems.
While these insights remain generally useful today, the phenomenal success of
random field models means that the kinds of inference problems that have to be
solved changed significantly. Specifically, the models today often include
higher order interactions, flexible connectivity structures, large
la\-bel-spaces of different cardinalities, or learned energy tables. To reflect
these changes, we provide a modernized and enlarged study. We present an
empirical comparison of 32 state-of-the-art optimization techniques on a corpus
of 2,453 energy minimization instances from diverse applications in computer
vision. To ensure reproducibility, we evaluate all methods in the OpenGM 2
framework and report extensive results regarding runtime and solution quality.
Key insights from our study agree with the results of Szeliski et al. for the
types of models they studied. However, on new and challenging types of models
our findings disagree and suggest that polyhedral methods and integer
programming solvers are competitive in terms of runtime and solution quality
over a large range of model types.
Bridging the Gap Between Synthetic and Real Data
M. Fritz
Machine Learning with Interdependent and Non-Identically Distributed Data, 2015
M. Fritz
Machine Learning with Interdependent and Non-Identically Distributed Data, 2015
Graphical Passwords in the Wild: Understanding How Users Choose Pictures and Passwords in Image-based Authentication Schemes
F. Alt, S. Schneegass, A. Shirazi, M. Hassib and A. Bulling
MobileHCI’15, 17th International Conference on Human-Computer Interaction with Mobile Devices and Services, 2015
F. Alt, S. Schneegass, A. Shirazi, M. Hassib and A. Bulling
MobileHCI’15, 17th International Conference on Human-Computer Interaction with Mobile Devices and Services, 2015
Characterizing Information Diets of Social Media Users
J. Kulshrestha, M. B. Zafar, L. E. Espin Noboa, K. Gummadi and S. Gosh
Proceedings of the 9th International AAAI Conference on Web and Social Media (ICWSM 2015), 2015
J. Kulshrestha, M. B. Zafar, L. E. Espin Noboa, K. Gummadi and S. Gosh
Proceedings of the 9th International AAAI Conference on Web and Social Media (ICWSM 2015), 2015
Latent Max-margin Metric Learning for Comparing Video Face Tubes
G. Sharma and P. Pérez
The IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2015), 2015
G. Sharma and P. Pérez
The IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2015), 2015
Hard to Cheat: A Turing Test based on Answering Questions about Images
M. Malinowski and M. Fritz
Twenty-Ninth AAAI Conference on Artificial Intelligence W6, Beyond the Turing Test (AAAI 2015 W6, Beyond the Turing Test), 2015
(arXiv: 1501.03302) M. Malinowski and M. Fritz
Twenty-Ninth AAAI Conference on Artificial Intelligence W6, Beyond the Turing Test (AAAI 2015 W6, Beyond the Turing Test), 2015
Abstract
Progress in language and image understanding by machines has sparkled the<br>interest of the research community in more open-ended, holistic tasks, and<br>refueled an old AI dream of building intelligent machines. We discuss a few<br>prominent challenges that characterize such holistic tasks and argue for<br>"question answering about images" as a particular appealing instance of such a<br>holistic task. In particular, we point out that it is a version of a Turing<br>Test that is likely to be more robust to over-interpretations and contrast it<br>with tasks like grounding and generation of descriptions. Finally, we discuss<br>tools to measure progress in this field.<br>
What Makes for Effective Detection Proposals?
J. Hosang, R. Benenson, P. Dollár and B. Schiele
Technical Report, 2015
(arXiv: 1502.05082) J. Hosang, R. Benenson, P. Dollár and B. Schiele
Technical Report, 2015
Abstract
Current top performing object detectors employ detection proposals to guide
the search for objects, thereby avoiding exhaustive sliding window search
across images. Despite the popularity and widespread use of detection
proposals, it is unclear which trade-offs are made when using them during
object detection. We provide an in-depth analysis of twelve proposal methods
along with four baselines regarding proposal repeatability, ground truth
annotation recall on PASCAL and ImageNet, and impact on DPM and R-CNN detection
performance. Our analysis shows that for object detection improving proposal
localisation accuracy is as important as improving recall. We introduce a novel
metric, the average recall (AR), which rewards both high recall and good
localisation and correlates surprisingly well with detector performance. Our
findings show common strengths and weaknesses of existing methods, and provide
insights and metrics for selecting and tuning proposal methods.
Richer Object Representations for Object Class Detection in Challenging Real World Image
B. Pepik
PhD Thesis, Universität des Saarlandes, 2015
B. Pepik
PhD Thesis, Universität des Saarlandes, 2015
GazeDPM: Early Integration of Gaze Information in Deformable Part Models
I. Shcherbatyi, A. Bulling and M. Fritz
Technical Report, 2015
(arXiv: 1505.05753) I. Shcherbatyi, A. Bulling and M. Fritz
Technical Report, 2015
Abstract
An increasing number of works explore collaborative human-computer systems in
which human gaze is used to enhance computer vision systems. For object
detection these efforts were so far restricted to late integration approaches
that have inherent limitations, such as increased precision without increase in
recall. We propose an early integration approach in a deformable part model,
which constitutes a joint formulation over gaze and visual data. We show that
our GazeDPM method improves over the state-of-the-art DPM baseline by 4% and a
recent method for gaze-supported object detection by 3% on the public POET
dataset. Our approach additionally provides introspection of the learnt models,
can reveal salient image structures, and allows us to investigate the interplay
between gaze attracting and repelling areas, the importance of view-specific
models, as well as viewers' personal biases in gaze patterns. We finally study
important practical aspects of our approach, such as the impact of using
saliency maps instead of real fixations, the impact of the number of fixations,
as well as robustness to gaze estimation error.
Labeled Pupils in the Wild: A Dataset for Studying Pupil Detection in Unconstrained Environments
M. Tonsen, X. Zhang, Y. Sugano and A. Bulling
Technical Report, 2015
(arXiv: 1511.05768) M. Tonsen, X. Zhang, Y. Sugano and A. Bulling
Technical Report, 2015
Abstract
We present labelled pupils in the wild (LPW), a novel dataset of 66
high-quality, high-speed eye region videos for the development and evaluation
of pupil detection algorithms. The videos in our dataset were recorded from 22
participants in everyday locations at about 95 FPS using a state-of-the-art
dark-pupil head-mounted eye tracker. They cover people with different
ethnicities, a diverse set of everyday indoor and outdoor illumination
environments, as well as natural gaze direction distributions. The dataset also
includes participants wearing glasses, contact lenses, as well as make-up. We
benchmark five state-of-the-art pupil detection algorithms on our dataset with
respect to robustness and accuracy. We further study the influence of image
resolution, vision aids, as well as recording location (indoor, outdoor) on
pupil detection performance. Our evaluations provide valuable insights into the
general pupil detection problem and allow us to identify key challenges for
robust pupil detection on head-mounted eye trackers.
2014
Pursuits: Spontaneous Eye-based Interaction for Dynamic Interfaces
M. Vidal, A. Bulling and H. Gellersen
ACM SIGMOBILE Mobile Computing and Communications Review, Volume 18, Number 4, 2014
M. Vidal, A. Bulling and H. Gellersen
ACM SIGMOBILE Mobile Computing and Communications Review, Volume 18, Number 4, 2014
Abstract
Although gaze is an attractive modality for pervasive
interaction, real-world implementation of eye-based interfaces poses
significant challenges. In particular, user calibration is tedious and
time consuming. Pursuits is an innovative interaction technique that
enables truly spontaneous interaction with eye-based interfaces. A user
can simply walk up to the screen and readily interact with moving
targets. Instead of being based on gaze location, Pursuits correlates
eye pursuit movements with objects dynamically moving on the interface.
A Multi-world Approach to Question Answering about Real-world Scenes based on Uncertain Input
M. Malinowski and M. Fritz
Advances in Neural Information Processing Systems 27 (NIPS 2014), 2014
M. Malinowski and M. Fritz
Advances in Neural Information Processing Systems 27 (NIPS 2014), 2014
Ubic: Bridging the Gap Between Digital Cryptography and the Physical World
M. Simkin, A. Bulling, M. Fritz and D. Schröder
Computer Security - ESORICS 2014, 2014
M. Simkin, A. Bulling, M. Fritz and D. Schröder
Computer Security - ESORICS 2014, 2014
Learning Human Pose Estimation Features with Convolutional Networks
A. Jain, J. Tompson, M. Andriluka, G. W. Taylor and C. Bregler
International Conference on Learning Representations 2014 (ICLR 2014), 2014
(arXiv: 1312.7302) A. Jain, J. Tompson, M. Andriluka, G. W. Taylor and C. Bregler
International Conference on Learning Representations 2014 (ICLR 2014), 2014
Abstract
This paper introduces a new architecture for human pose estimation using a
multi- layer convolutional network architecture and a modified learning
technique that learns low-level features and higher-level weak spatial models.
Unconstrained human pose estimation is one of the hardest problems in computer
vision, and our new architecture and learning schema shows significant
improvement over the current state-of-the-art results. The main contribution of
this paper is showing, for the first time, that a specific variation of deep
learning is able to outperform all existing traditional architectures on this
task. The paper also discusses several lessons learned while researching
alternatives, most notably, that it is possible to learn strong low-level
feature detectors on features that might even just cover a few pixels in the
image. Higher-level spatial models improve somewhat the overall result, but to
a much lesser extent then expected. Many researchers previously argued that the
kinematic structure and top-down information is crucial for this domain, but
with our purely bottom up, and weak spatial model, we could improve other more
complicated architectures that currently produce the best results. This mirrors
what many other researchers, like those in the speech recognition, object
recognition, and other domains have experienced.
Multi-view Priors for Learning Detectors from Sparse Viewpoint Data
B. Pepik, M. Stark, P. Gehler and B. Schiele
International Conference on Learning Representations 2014 (ICLR 2014), 2014
(arXiv: 1312.6095) B. Pepik, M. Stark, P. Gehler and B. Schiele
International Conference on Learning Representations 2014 (ICLR 2014), 2014
Abstract
While the majority of today's object class models provide only 2D bounding
boxes, far richer output hypotheses are desirable including viewpoint,
fine-grained category, and 3D geometry estimate. However, models trained to
provide richer output require larger amounts of training data, preferably well
covering the relevant aspects such as viewpoint and fine-grained categories. In
this paper, we address this issue from the perspective of transfer learning,
and design an object class model that explicitly leverages correlations between
visual features. Specifically, our model represents prior distributions over
permissible multi-view detectors in a parametric way -- the priors are learned
once from training data of a source object class, and can later be used to
facilitate the learning of a detector for a target class. As we show in our
experiments, this transfer is not only beneficial for detectors based on
basic-level category representations, but also enables the robust learning of
detectors that represent classes at finer levels of granularity, where training
data is typically even scarcer and more unbalanced. As a result, we report
largely improved performance in simultaneous 2D object localization and
viewpoint estimation on a recent dataset of challenging street scenes.
Multi-View Priors for Learning Detectors from Sparse Viewpoint Data
B. Pepik, M. Stark, P. Gehler and B. Schiele
International Conference on Learning Representations 2014 (ICLR 2014), 2014
(arXiv: http://arxiv.org/abs/1312.6095) B. Pepik, M. Stark, P. Gehler and B. Schiele
International Conference on Learning Representations 2014 (ICLR 2014), 2014
Abstract
While the majority of today's object class models provide only 2D bounding boxes, far richer output hypotheses are desirable including viewpoint, fine-grained category, and 3D geometry estimate. However, models trained to provide richer output require larger amounts of training data, preferably well covering the relevant aspects such as viewpoint and fine-grained categories. In this paper, we address this issue from the perspective of transfer learning, and design an object class model that explicitly leverages correlations between visual features. Specifically, our model represents prior distributions over permissible multi-view detectors in a parametric way -- the priors are learned once from training data of a source object class, and can later be used to facilitate the learning of a detector for a target class. As we show in our experiments, this transfer is not only beneficial for detectors based on basic-level category representations, but also enables the robust learning of detectors that represent classes at finer levels of granularity, where training data is typically even scarcer and more unbalanced. As a result, we report largely improved performance in simultaneous 2D object localization and viewpoint estimation on a recent dataset of challenging street scenes.
Introduction to the PETMEI Special Issue
A. Bulling and R. Bednarik
Journal of Eye Movement Research, Volume 7, Number 3, 2014
A. Bulling and R. Bednarik
Journal of Eye Movement Research, Volume 7, Number 3, 2014
Candidate Sampling for Neuron Reconstruction from Anisotropic Electron Microscopy Volumes
J. Funke, J. N. P. Martel, S. Gerhard, B. Andres, D. C. Ciresan, A. Giusti, L. M. Gambardella, J. Schmidhuber, H. Pfister, A. Cardona and M. Cook
Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2014, 2014
J. Funke, J. N. P. Martel, S. Gerhard, B. Andres, D. C. Ciresan, A. Giusti, L. M. Gambardella, J. Schmidhuber, H. Pfister, A. Cardona and M. Cook
Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2014, 2014
Towards a Visual Turing Challenge
M. Malinowski and M. Fritz
NIPS 2014 Workshop on Learning Semantics, 2014
(arXiv: 1410.8027) M. Malinowski and M. Fritz
NIPS 2014 Workshop on Learning Semantics, 2014
Abstract
As language and visual understanding by machines progresses rapidly, we are observing an increasing interest in holistic architectures that tightly interlink both modalities in a joint learning and inference process. This trend has allowed the community to progress towards more challenging and open tasks and refueled the hope at achieving the old AI dream of building machines that could pass a turing test in open domains. In order to steadily make progress towards this goal, we realize that quantifying performance becomes increasingly difficult. Therefore we ask how we can precisely define such challenges and how we can evaluate different algorithms on this open tasks? In this paper, we summarize and discuss such challenges as well as try to give answers where appropriate options are available in the literature. We exemplify some of the solutions on a recently presented dataset of question-answering task based on real-world indoor images that establishes a visual turing challenge. Finally, we argue despite the success of unique ground-truth annotation, we likely have to step away from carefully curated dataset and rather rely on ’}social consensus{’ as the main driving force to create suitable benchmarks. Providing coverage in this inherently ambiguous output space is an emerging challenge that we face in order to make quantifiable progress in this area.
Expressive Models and Comprehensive Benchmark for 2D Human Pose Estimation
L. Pishchulin, M. Andriluka, P. Gehler and B. Schiele
Parts and Attributes (ECCV 2014 Workshop PA), 2014
L. Pishchulin, M. Andriluka, P. Gehler and B. Schiele
Parts and Attributes (ECCV 2014 Workshop PA), 2014
In the Blink of an Eye - Combining Head Motion and Eye Blink Frequency for Activity Recognition with Google Glass
S. Ishimaru, K. Kunze, K. Kise, J. Weppner, A. Dengel, P. Lukowicz and A. Bulling
Proceedings of the 5th Augmented Human International Conference (AH 2014), 2014
S. Ishimaru, K. Kunze, K. Kise, J. Weppner, A. Dengel, P. Lukowicz and A. Bulling
Proceedings of the 5th Augmented Human International Conference (AH 2014), 2014
Object Disambiguation for Augmented Reality Applications
W.-C. Chiu, G. Johnson, D. McCulley, O. Grau and M. Fritz
Proceedings of the British Machine Vision Conference (BMVC 2014), 2014
W.-C. Chiu, G. Johnson, D. McCulley, O. Grau and M. Fritz
Proceedings of the British Machine Vision Conference (BMVC 2014), 2014
How Good are Detection Proposals, really?
J. Hosang, R. Benenson and B. Schiele
Proceedings of the British Machine Vision Conference (BMVC 2014), 2014
J. Hosang, R. Benenson and B. Schiele
Proceedings of the British Machine Vision Conference (BMVC 2014), 2014
Abstract
Current top performing Pascal VOC object detectors employ detection proposals to guide the search for objects thereby avoiding exhaustive sliding window search across images. Despite the popularity of detection proposals, it is unclear which trade‐offs are made when using them during object detection. We provide an in depth analysis of ten object proposal methods along with four baselines regarding ground truth annotation recall (on Pascal VOC 2007 and ImageNet 2013), repeatability, and impact on DPM detector performance. Our findings show common weaknesses of existing methods, and provide insights to choose the most adequate method for different settings.
Scalable Multitask Representation Learning for Scene Classification
M. Lapin, B. Schiele and M. Hein
Scene Understanding Workshop (SUNw 2014), 2014
M. Lapin, B. Schiele and M. Hein
Scene Understanding Workshop (SUNw 2014), 2014
Learning People Detectors for Tracking in Crowded Scenes
S. Tang, M. Andriluka, A. Milan, K. Schindler, S. Roth and B. Schiele
Scene Understanding Workshop (SUNw 2014), 2014
S. Tang, M. Andriluka, A. Milan, K. Schindler, S. Roth and B. Schiele
Scene Understanding Workshop (SUNw 2014), 2014
High-Resolution 3D Layout from a Single View
M. Z. Zia, M. Stark and K. Schindler
Scene Understanding Workshop (SUNw 2014), 2014
M. Z. Zia, M. Stark and K. Schindler
Scene Understanding Workshop (SUNw 2014), 2014
Pupil: An Open Source Platform for Pervasive Eye Tracking and Mobile Gaze-based Interaction
M. Kassner, W. Patera and A. Bulling
UbiComp’14 Adjunct, 2014
M. Kassner, W. Patera and A. Bulling
UbiComp’14 Adjunct, 2014
Physically Grounded 3D Scene Interpretation with Detailed Object Models
M. Z. Zia, M. Stark and K. Schindler
Vision Meets Cognition Workshop: Functionality, Physics, Intentionality, and Causality (CVPR 2014 Workshop FPIC), 2014
M. Z. Zia, M. Stark and K. Schindler
Vision Meets Cognition Workshop: Functionality, Physics, Intentionality, and Causality (CVPR 2014 Workshop FPIC), 2014
Zero-Shot Learning with Structured Embeddings
Z. Akata, H. Lee and B. Schiele
Technical Report, 2014
(arXiv: 1409.8403) Z. Akata, H. Lee and B. Schiele
Technical Report, 2014
Abstract
Despite significant recent advances in image classification, fine-grained
classification remains a challenge. In the present paper, we address the
zero-shot and few-shot learning scenarios as obtaining labeled data is
especially difficult for fine-grained classification tasks. First, we embed
state-of-the-art image descriptors in a label embedding space using side
information such as attributes. We argue that learning a joint embedding space,
that maximizes the compatibility between the input and output embeddings, is
highly effective for zero/few-shot learning. We show empirically that such
embeddings significantly outperforms the current state-of-the-art methods on
two challenging datasets (Caltech-UCSD Birds and Animals with Attributes).
Second, to reduce the amount of costly manual attribute annotations, we use
alternate output embeddings based on the word-vector representations, obtained
from large text-corpora without any supervision. We report that such
unsupervised embeddings achieve encouraging results, and lead to further
improvements when combined with the supervised ones.
Learning Multi-scale Representations for Material Classification
W. Li and M. Fritz
Technical Report, 2014
(arXiv: 1408.2938) W. Li and M. Fritz
Technical Report, 2014
Abstract
The recent progress in sparse coding and deep learning has made unsupervised
feature learning methods a strong competitor to hand-crafted descriptors. In
computer vision, success stories of learned features have been predominantly
reported for object recognition tasks. In this paper, we investigate if and how
feature learning can be used for material recognition. We propose two
strategies to incorporate scale information into the learning procedure
resulting in a novel multi-scale coding procedure. Our results show that our
learned features for material recognition outperform hand-crafted descriptors
on the FMD and the KTH-TIPS2 material classification benchmarks.
A Pooling Approach to Modelling Spatial Relations for Image Retrieval and Annotation
M. Malinowski and M. Fritz
Technical Report, 2014
(arXiv: 1411.5190) M. Malinowski and M. Fritz
Technical Report, 2014
Abstract
Over the last two decades we have witnessed strong progress on modeling
visual object classes, scenes and attributes that have significantly
contributed to automated image understanding. On the other hand, surprisingly
little progress has been made on incorporating a spatial representation and
reasoning in the inference process. In this work, we propose a pooling
interpretation of spatial relations and show how it improves image retrieval
and annotations tasks involving spatial language. Due to the complexity of the
spatial language, we argue for a learning-based approach that acquires a
representation of spatial relations by learning parameters of the pooling
operator. We show improvements on previous work on two datasets and two
different tasks as well as provide additional insights on a new dataset with an
explicit focus on spatial relations.
Estimating Maximally Probable Constrained Relations by Mathematical Programming
L. Qu and B. Andres
Technical Report, 2014
(arXiv: 1408.0838) L. Qu and B. Andres
Technical Report, 2014
Abstract
Estimating a constrained relation is a fundamental problem in machine
learning. Special cases are classification (the problem of estimating a map
from a set of to-be-classified elements to a set of labels), clustering (the
problem of estimating an equivalence relation on a set) and ranking (the
problem of estimating a linear order on a set). We contribute a family of
probability measures on the set of all relations between two finite, non-empty
sets, which offers a joint abstraction of multi-label classification,
correlation clustering and ranking by linear ordering. Estimating (learning) a
maximally probable measure, given (a training set of) related and unrelated
pairs, is a convex optimization problem. Estimating (inferring) a maximally
probable relation, given a measure, is a 01-linear program. It is solved in
linear time for maps. It is NP-hard for equivalence relations and linear
orders. Practical solutions for all three cases are shown in experiments with
real data. Finally, estimating a maximally probable measure and relation
jointly is posed as a mixed-integer nonlinear program. This formulation
suggests a mathematical programming approach to semi-supervised learning.
Combining Visual Recognition and Computational Linguistics : Linguistic Knowledge for Visual Recognition and Natural Language Descriptions of Visual Content
M. Rohrbach
PhD Thesis, Universität des Saarlandes, 2014
M. Rohrbach
PhD Thesis, Universität des Saarlandes, 2014
Coherent Multi-sentence Video Description with Variable Level of Detail
A. Senina, M. Rohrbach, W. Qiu, A. Friedrich, S. Amin, M. Andriluka, M. Pinkal and B. Schiele
Technical Report, 2014
(arXiv: 1403.6173) A. Senina, M. Rohrbach, W. Qiu, A. Friedrich, S. Amin, M. Andriluka, M. Pinkal and B. Schiele
Technical Report, 2014
Abstract
Humans can easily describe what they see in a coherent way and at varying
level of detail. However, existing approaches for automatic video description
are mainly focused on single sentence generation and produce descriptions at a
fixed level of detail. In this paper, we address both of these limitations: for
a variable level of detail we produce coherent multi-sentence descriptions of
complex videos. We follow a two-step approach where we first learn to predict a
semantic representation (SR) from video and then generate natural language
descriptions from the SR. To produce consistent multi-sentence descriptions, we
model across-sentence consistency at the level of the SR by enforcing a
consistent topic. We also contribute both to the visual recognition of objects
proposing a hand-centric approach as well as to the robust generation of
sentences using a word lattice. Human judges rate our multi-sentence
descriptions as more readable, correct, and relevant than related work. To
understand the difference between more detailed and shorter descriptions, we
collect and analyze a video description corpus of three levels of detail.
2013
Transfer Learning in a Transductive Setting
M. Rohrbach, S. Ebert and B. Schiele
Advances in Neural Information Processing Systems 26 (NIPS 2013), 2013
M. Rohrbach, S. Ebert and B. Schiele
Advances in Neural Information Processing Systems 26 (NIPS 2013), 2013
Abstract
Category models for objects or activities typically rely on supervised
learning requiring sufficiently large training sets. Transferring
knowledge from known categories to novel classes with no or only
a few labels however is far less researched even though it is a common
scenario. In this work, we extend transfer learning with semi-supervised
learning to exploit unlabeled instances of (novel) categories with
no or only a few labeled instances. Our proposed approach Propagated
Semantic Transfer combines three main ingredients. First, we transfer
information from known to novel categories by incorporating external
knowledge, such as linguistic or expert-specified information, e.g.,
by a mid-level layer of semantic attributes. Second, we exploit the
manifold structure of novel classes. More specifically we adapt a
graph-based learning algorithm - so far only used for semi-supervised
learning - to zero-shot and few-shot learning. Third, we improve
the local neighborhood in such graph structures by replacing the
raw feature-based representation with a mid-level object- or attribute-based
representation. We evaluate our approach on three challenging datasets
in two different applications, namely on Animals with Attributes
and ImageNet for image classification and on MPII Composites for
activity recognition. Our approach consistently outperforms state-of-the-art
transfer and semi-supervised approaches on all datasets.
EyeContext: Recognition of High-level Contextual Cues from Human Visual Behaviour
A. Bulling, C. Weichel and H. Gellersen
CHI 2013, The 31st Annual CHI Conference on Human Factors in Computing Systems, 2013
A. Bulling, C. Weichel and H. Gellersen
CHI 2013, The 31st Annual CHI Conference on Human Factors in Computing Systems, 2013
Abstract
Automatic annotation of life logging data is challenging. In this
work we present EyeContext, a system to infer high-level contextual
cues from human visual behaviour. We conduct a user study to record
eye movements of four participants over a full day of their daily
life, totalling 42.5 hours of eye movement data. Participants were
asked to self-annotate four non-mutually exclusive cues: social (interacting
with somebody vs. no interaction), cognitive (concentrated work vs.
leisure), physical (physically active vs. not active), and spatial
(inside vs. outside a building). We evaluate a proof-of-concept EyeContext
system that combines encoding of eye movements into strings and a
spectrum string kernel support vector machine (SVM) classifier. Using
person-dependent training, we obtain a top performance of 85.3%
precision (98.0% recall) for recognising social interactions. Our
results demonstrate the large information content available in long-term
human visual behaviour and opens up new venues for research on eye-based
behavioural monitoring and life logging.
Pursuits: Eye-based Interaction with Moving Targets
M. Vidal, K. Pfeuffer, A. Bulling and H. W. Gellersen
CHI 2013 Extended Abstracts, 2013
M. Vidal, K. Pfeuffer, A. Bulling and H. W. Gellersen
CHI 2013 Extended Abstracts, 2013
Abstract
Eye-based interaction has commonly been based on estimation of eye
gaze direction, to locate objects for interaction. We introduce Pursuits,
a novel and very different eye tracking method that instead is based
on following the trajectory of eye movement and comparing this with
trajectories of objects in the field of view. Because the eyes naturally
follow the trajectory of moving objects of interest, our method is
able to detect what the user is looking at, by matching eye movement
and object movement. We illustrate Pursuits with three applications
that demonstrate how the method facilitates natural interaction with
moving targets.
Learning Smooth Pooling Regions for Visual Recognition
M. Malinowski and M. Fritz
Electronic Proceedings of the British Machine Vision Conference 2013 (BMVC 2013), 2013
M. Malinowski and M. Fritz
Electronic Proceedings of the British Machine Vision Conference 2013 (BMVC 2013), 2013
Abstract
From the early HMAX model to Spatial Pyramid Matching, spatial pooling
has played an important role in visual recognition pipelines. By
aggregating local statistics, it equips the recognition pipelines
with a certain degree of robustness to translation and deformation
yet preserving spatial information. Despite of its predominance in
current recognition systems, we have seen little progress to fully
adapt the pooling strategy to the task at hand. In this paper, we
propose a flexible parameterization of the spatial pooling step and
learn the pooling regions together with the classifier. We investigate
a smoothness regularization term that in conjuncture with an efficient
learning scheme makes learning scalable. Our framework can work with
both popular pooling operators: sum-pooling and max-pooling. Finally,
we show benefits of our approach for object recognition tasks based
on visual words and higher level event recognition tasks based on
object-bank features. In both cases, we improve over the hand-crafted
spatial pooling step showing the importance of its adaptation to
the task.
Segmenting Planar Superpixel Adjacency Graphs w.r.t. Non-planar Superpixel Affinity Graphs
B. Andres, J. Yarkony, B. S. Manjunath, S. Kirchhoff, E. Turetken, C. C. Fowlkes and H. Pfister
Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR 2013), 2013
B. Andres, J. Yarkony, B. S. Manjunath, S. Kirchhoff, E. Turetken, C. C. Fowlkes and H. Pfister
Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR 2013), 2013
Eye Pull, Eye Push: Moving Objects between Large Screens and Personal Devices with Gaze & Touch
J. Turner, J. Alexander, A. Bulling, S. Dominik and H. Gellersen
Human-Computer Interaction – INTERACT 2013, 2013
J. Turner, J. Alexander, A. Bulling, S. Dominik and H. Gellersen
Human-Computer Interaction – INTERACT 2013, 2013
Abstract
Previous work has validated the eyes and mobile input as a viable
approach for pointing at, and selecting out of reach objects. This
work presents Eye Pull, Eye Push, a novel interaction concept for
content transfer between public and personal devices using gaze and
touch. We present three techniques that enable this interaction:
Eye Cut & Paste, Eye Drag & Drop, and Eye Summon & Cast. We outline
and discuss several scenarios in which these techniques can be used.
In a user study we found that participants responded well to the
visual feedback provided by Eye Drag & Drop during object movement.
In contrast, we found that although Eye Summon & Cast significantly
improved performance, participants had difficulty coordinating their
hands and eyes during interaction.
Translating Video Content to Natural Language Descriptions
M. Rohrbach, W. Qiu, I. Titov, S. Thater, M. Pinkal and B. Schiele
ICCV 2013, IEEE International Conference on Computer Vision, 2013
M. Rohrbach, W. Qiu, I. Titov, S. Thater, M. Pinkal and B. Schiele
ICCV 2013, IEEE International Conference on Computer Vision, 2013
Abstract
Humans use rich natural language to describe and communicate visual
perceptions. In order to provide natural language descriptions for
visual content, this paper combines two important ingredients. First,
we generate a rich semantic representation of the visual content
including e.g. object and activity labels. To predict the semantic
representation we learn a CRF to model the relationships between
different components of the visual input. And second, we propose
to formulate the generation of natural language as a machine translation
problem using the semantic representation as source language and
the generated sentences as target language. For this we exploit the
power of a parallel corpus of videos and textual descriptions and
adapt statistical machine translation to translate between ou