Margret Keuper (Research Leader)

Prof. Dr. Margret Keuper

Address
Max-Planck-Institut für Informatik
Saarland Informatics Campus
Campus E1 4
66123 Saarbrücken
Location
E1 4 - 617
Phone
+49 681 9325 2117
Fax
+49 681 9325 2099

Publications

2024

  1. Conference paper
    D2
    “Improving Feature Stability during Upsampling - Spectral Artifacts and the Importance of Spatial Context,” in Computer Vision -- ECCV 2024, Milano, Italy, 2024.
  2. Conference paper
    D2
    “Domain-Aware Fine-Tuning of Foundation Models,” in ICML 2024 Workshop on Foundation Models in the Wild (ICML 2024 FM-Wild Workshop), Vienna, Austria, 2024.
  3. Conference paper
    D2
    “Task Driven Sensor Layouts - Joint Optimization of Pixel Layout and Network Parameters,” in IEEE International Conference on Computational Photography (ICCP 2024), Lausanne, Switzrland, 2024.
  4. Article
    D2
    “Intra- & Extra-Source Exemplar-Based Style Synthesis for Improved Domain Generalization,” International Journal of Computer Vision, vol. 132, 2024.
  5. Conference paper
    D2
    “CosPGD: An Efficient White-Box Adversarial Attack for Pixel-Wise Prediction Tasks,” in Proceedings of the 41st International Conference on Machine Learning (ICML 2024), Vienna, Austria, 2024.
  6. Conference paper
    D2
    “Implicit Representations for Constrained Image Segmentation,” in Proceedings of the 41st International Conference on Machine Learning (ICML 2024), Vienna, Austria, 2024.
  7. Conference paper
    D2
    “MultiMax: Sparse and Mulit-Modal Attention Learning,” in Proceedings of the 41st International Conference on Machine Learning (ICML 2024), Vienna, Austria, 2024.
  8. Conference paper
    D2
    “Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrive,” in The Twelfth International Conference on Learning Representations (ICLR 2024), Vienna, Austria, 2024.
  9. Article
    D2
    “Learning the essential in less than 2k additional weights - a simple approach to improve image classification stability under corruptions,” Transactions on Machine Learning Research, vol. 2024, no. 6, 2024.
  10. Article
    D2
    “As large as it gets - Studying Infinitely Large Convolutions via Neural Implicit Frequency Filters,” Transactions on Machine Learning Research, vol. 2024, 2024.

2023

  1. Conference paper
    D2
    “Differentiable Architecture Search: a One-Shot Method?,” in AutoML Conference 2023, Potsdam/Berlin, Germany, 2023.
  2. Conference paper
    D2
    “Neural Architecture Design and Robustness: A Dataset,” in Eleventh International Conference on Learning Representations (ICLR 2023), Kigali, Rwanda.
  3. Conference paper
    D2
    “On the Unreasonable Vulnerability of Transformers for Image Restoration – and an Easy Fix,” in IEEE/CVF International Conference on Computer Vision Workshops (ICCVW 2023), Paris, France, 2023.
  4. Conference paper
    D2
    “Classification Robustness to Common Optical Aberrations,” in IEEE/CVF International Conference on Computer Vision Workshops (ICCVW 2023), Paris, France, 2023.
  5. Article
    D2
    “Higher-Order Multicuts for Geometric Model Fitting and Motion Segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 1, 2023.
  6. Conference paper
    D2
    “Intra-Source Style Augmentation for Improved Domain Generalization,” in 2023 IEEE Winter Conference on Applications of Computer Vision (WACV 2023), Waikoloa Village, HI, USA, 2023.
  7. Article
    D2
    “Improving Primary-Vertex Reconstruction with a Minimum-Cost Lifted Multicut Graph Partitioning Algorithm,” Journal of Instrumentation, vol. 18, 2023.
  8. Conference paper
    D2
    “Towards Understanding Climate Change Perceptions: A Social Media Dataset,” in NeurIPS 2023 Workshop on Tackling Climate Change with Machine Learning, New Orleans, LA, USA, 2023.
  9. Conference paper
    D2
    “An Evaluation of Zero-Cost Proxies - From Neural Architecture Performance Prediction to Model Robustness,” in Pattern Recognition (DAGM GCPR 2023), Heidelberg, Germany, 2023.
  10. Conference paper
    D2
    “FullFormer: Generating Shapes Inside Shapes,” in Pattern Recognition (DAGM GCPR 2023), Heidelberg, Germany, 2023.
  11. Article
    D2
    “Improving Native CNN Robustness with Filter Frequency Regularization,” Transactions on Machine Learning Research, vol. 2023, 2023.
  12. Conference paper
    D2
    “Implicit Representations for Image Segmentation,” in UniReps: The First Workshop on Unifying Representations in Neural Models, New Orleans, LA, USA, 2022.

2022

  1. Conference paper
    D2
    “SP-ViT: Learning 2D Spatial Priors for Vision Transformers,” in 33rd British Machine Vision Conference (BMVC 2022), London, UK, 2022.
  2. Conference paper
    D2
    “Robust Models are less Over-Confident,” in Advances in Neural Information Processing Systems 35 (NeurIPS 2022), New Orleans, LA, USA, 2022.
  3. Conference paper
    D2
    “Trading off Image Quality for Robustness is not Necessary with Regularized Deterministic Autoencoders,” in Advances in Neural Information Processing Systems 35 (NeurIPS 2022), New Orleans, LA, USA, 2022.
  4. Conference paper
    D2
    “FrequencyLowCut Pooling - Plug & Play against Catastrophic Overfitting,” in Computer Vision -- ECCV 2022, Tel Aviv, Israel, 2022.
  5. Conference paper
    D2
    “Learning Where To Look - Generative NAS is Surprisingly Efficient,” in Computer Vision -- ECCV 2022, Tel Aviv, Israel, 2022.
  6. Article
    D2
    “Aliasing and Adversarial Robust Generalization of CNNs,” Machine Learning, vol. 111, 2022.
  7. Conference paper
    D2
    “Learning to solve Minimum Cost Multicuts efficiently using Edge-Weighted Graph Convolutional Neural Networks,” in Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2022), Grenoble, France, 2022.
  8. Conference paper
    D2
    “Impact of Realistic Properties of the Point Spread Function on Classification Tasks to Reveal a Possible Distribution Shift,” in NeurIPS 2022 Workshop on Distribution Shifts: Connecting Methods and Applications (NeurIPS 2022 Workshop DistShift), New Orelans, LA, USA, 2022.
  9. Conference paper
    D2
    “Optimizing Edge Detection for Image Segmentation with Multicut Penalties,” in Pattern Recognition (DAGM GCPR 2022), Konstanz, Germany, 2022.
  10. Paper
    D2
    “Hypergraph Transformer for Skeleton-based Action Recognition,” 2022. [Online]. Available: https://arxiv.org/abs/2211.09590.

2021

  1. Conference paper
    D2
    “Shape your Space: A Gaussian Mixture Regularization Approach to Deterministic Autoencoders,” in Advances in Neural Information Processing Systems 34 pre-proceedings (NeurIPS 2021), Virtual Event, 2021.
  2. Conference paper
    D2
    “DARTS for Inverse Problems: a Study on Stability,” in NeurIPS 2021 Workshop on Deep Learning and Inverse Problems (NeurIPS 2021 Deep Inverse Workshop), Virtual, 2021.
  3. Conference paper
    D2
    “Internalized Biases in Fréchet Inception Distance,” in NeurIPS 2021 Workshop on Distribution Shifts: Connecting Methods and Applications (NeurIPS 2021 Workshop DistShift), Virtual, 2021.
  4. Conference paper
    D2
    “Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis,” in Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (IJCAI 2021), Montreal, Canada, 2021.
  5. Conference paper
    D2
    “Spectral Distribution Aware Image Generation,” in Thirty-Fifth AAAI Conference on Artificial Intelligence Technical Tracks 2, Virtual Conference, 2021.

2017

  1. Conference paper
    D2
    “STD2P: RGBD Semantic Segmentation Using Spatio-Temporal Data-Driven Pooling,” in 30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017), Honolulu, HI, USA, 2017.
  2. Conference paper
    D2
    “Learning Dilation Factors for Semantic Segmentation of Street Scenes,” in Pattern Recognition (GCPR 2017), Basel, Switzerland, 2017.

2016

  1. Paper
    D2
    “RGBD Semantic Segmentation Using Spatio-Temporal Data-Driven Pooling,” 2016. [Online]. Available: http://arxiv.org/abs/1604.02388.

2015

  1. Conference paper
    D2
    “Efficient Decomposition of Image and Mesh Graphs by Lifted Multicuts,” in ICCV 2015, IEEE International Conference on Computer Vision, Santiago, Chile, 2015.
  2. Conference paper
    D2
    “Motion Trajectory Segmentation via Minimum Cost Multicuts,” in ICCV 2015, IEEE International Conference on Computer Vision, Santiago, Chile, 2015.