Deep neural network (DNN) accelerators received considerable attention in past years due to saved energy compared to mainstream hardware. Low-voltage operation of DNN accelerators allows to further reduce energy consumption significantly, however, causes bit-level failures in the memory storing the quantized DNN weights. In this paper, we show that a combination of robust fixed-point quantization, weight clipping, and random bit error training (RandBET) improves robustness against random bit errors in (quantized) DNN weights significantly. This leads to high energy savings from both low-voltage operation as well as low-precision quantization. Our approach generalizes across operating voltages and accelerators, as demonstrated on bit errors from profiled SRAM arrays. We also discuss why weight clipping alone is already a quite effective way to achieve robustness against bit errors. Moreover, we specifically discuss the involved trade-offs regarding accuracy, robustness and precision: Without losing more than 1% in accuracy compared to a normally trained 8-bit DNN, we can reduce energy consumption on CIFAR-10 by 20%. Higher energy savings of, e.g., 30%, are possible at the cost of 2.5% accuracy, even for 4-bit DNNs.

Text and images are the two most common data modalities found on the Internet. Understanding the synergy between text and images, that is, seamlessly analyzing information from these modalities may be trivial for humans, but is challenging for software systems. In this dissertation we study problems where deciphering text-image synergy is crucial for finding solutions. We propose methods and ideas that establish semantic connections between text and images in multimodal contents, and empirically show their effectiveness in four interconnected problems: Image Retrieval, Image Tag Refinement, Image-Text Alignment, and Image Captioning. Our promising results and observations open up interesting scopes for future research involving text-image data understanding.Text and images are the two most common data modalities found on the Internet. Understanding the synergy between text and images, that is, seamlessly analyzing information from these modalities may be trivial for humans, but is challenging for software systems. In this dissertation we study problems where deciphering text-image synergy is crucial for finding solutions. We propose methods and ideas that establish semantic connections between text and images in multimodal contents, and empirically show their effectiveness in four interconnected problems: Image Retrieval, Image Tag Refinement, Image-Text Alignment, and Image Captioning. Our promising results and observations open up interesting scopes for future research involving text-image data understanding.

Humans can robustly recognize and localize objects by using visual and/or auditory cues. While machines are able to do the same with visual data already, less work has been done with sounds. This work develops an approach for scene understanding purely based on binaural sounds. The considered tasks include predicting the semantic masks of sound-making objects, the motion of sound-making objects, and the depth map of the scene. To this aim, we propose a novel sensor setup and record a new audio-visual dataset of street scenes with eight professional binaural microphones and a 360-degree camera. The co-existence of visual and audio cues is leveraged for supervision transfer. In particular, we employ a cross-modal distillation framework that consists of multiple vision teacher methods and a sound student method -- the student method is trained to generate the same results as the teacher methods do. This way, the auditory system can be trained without using human annotations. To further boost the performance, we propose another novel auxiliary task, coined Spatial Sound Super-Resolution, to increase the directional resolution of sounds. We then formulate the four tasks into one end-to-end trainable multi-tasking network aiming to boost the overall performance. Experimental results show that 1) our method achieves good results for all four tasks, 2) the four tasks are mutually beneficial -- training them together achieves the best performance, 3) the number and orientation of microphones are both important, and 4) features learned from the standard spectrogram and features obtained by the classic signal processing pipeline are complementary for auditory perception tasks. The data and code are released.

Training deep networks for semantic segmentation requires large amounts of labeled training data, which presents a major challenge in practice, as labeling segmentation masks is a highly labor-intensive process. To address this issue, we present a framework for semi-supervised and domain-adaptive semantic segmentation, which is enhanced by self-supervised monocular depth estimation (SDE) trained only on unlabeled image sequences. In particular, we utilize SDE as an auxiliary task comprehensively across the entire learning framework: First, we automatically select the most useful samples to be annotated for semantic segmentation based on the correlation of sample diversity and difficulty between SDE and semantic segmentation. Second, we implement a strong data augmentation by mixing images and labels using the geometry of the scene. Third, we transfer knowledge from features learned during SDE to semantic segmentation by means of transfer and multi-task learning. And fourth, we exploit additional labeled synthetic data with Cross-Domain DepthMix and Matching Geometry Sampling to align synthetic and real data. We validate the proposed model on the Cityscapes dataset, where all four contributions demonstrate significant performance gains, and achieve state-of-the-art results for semi-supervised semantic segmentation as well as for semi-supervised domain adaptation. In particular, with only 1/30 of the Cityscapes labels, our method achieves 92% of the fully-supervised baseline performance and even 97% when exploiting additional data from GTA. The source code is available at https://github.com/lhoyer/improving_segmentation_with_selfsupervised_depth.

Tracking of objects in 3D is a fundamental task in computer vision that finds use in a wide range of applications such as autonomous driving, robotics or augmented reality. Most recent approaches for 3D multi object tracking (MOT) from LIDAR use object dynamics together with a set of handcrafted features to match detections of objects. However, manually designing such features and heuristics is cumbersome and often leads to suboptimal performance. In this work, we instead strive towards a unified and learning based approach to the 3D MOT problem. We design a graph structure to jointly process detection and track states in an online manner. To this end, we employ a Neural Message Passing network for data association that is fully trainable. Our approach provides a natural way for track initialization and handling of false positive detections, while significantly improving track stability. We show the merit of the proposed approach on the publicly available nuScenes dataset by achieving state-of-the-art performance of 65.6% AMOTA and 58% fewer ID-switches.

Modern approaches to pose and body shape estimation have recently achieved strong performance even under challenging real-world conditions. Even from a single image of a clothed person, a realistic looking body shape can be inferred that captures a users' weight group and body shape type well. This opens up a whole spectrum of applications -- in particular in fashion -- where virtual try-on and recommendation systems can make use of these new and automatized cues. However, a realistic depiction of the undressed body is regarded highly private and therefore might not be consented by most people. Hence, we ask if the automatic extraction of such information can be effectively evaded. While adversarial perturbations have been shown to be effective for manipulating the output of machine learning models -- in particular, end-to-end deep learning approaches -- state of the art shape estimation methods are composed of multiple stages. We perform the first investigation of different strategies that can be used to effectively manipulate the automatic shape estimation while preserving the overall appearance of the original image.

Current datasets for video-based person re-identification (re-ID) do not include structural knowledge in form of human pose annotations for the persons of interest. Nonetheless, pose information is very helpful to disentangle useful feature information from background or occlusion noise. Especially real-world scenarios, such as surveillance, contain a lot of occlusions in human crowds or by obstacles. On the other hand, video-based person re-ID can benefit other tasks such as multi-person pose tracking in terms of robust feature matching. For that reason, we present PoseTrackReID, a large-scale dataset for multi-person pose tracking and video-based person re-ID. With PoseTrackReID, we want to bridge the gap between person re-ID and multi-person pose tracking. Additionally, this dataset provides a good benchmark for current state-of-the-art methods on multi-frame person re-ID.

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.

Personal photos of individuals when shared online, apart from exhibiting a myriad of memorable details, also reveals a wide range of private information and potentially entails privacy risks (e.g., online harassment, tracking). To mitigate such risks, it is crucial to study techniques that allow individuals to limit the private information leaked in visual data. We tackle this problem in a novel image obfuscation framework: to maximize entropy on inferences over targeted privacy attributes, while retaining image fidelity. We approach the problem based on an encoder-decoder style architecture, with two key novelties: (a) introducing a discriminator to perform bi-directional translation simultaneously from multiple unpaired domains; (b) predicting an image interpolation which maximizes uncertainty over a target set of attributes. We find our approach generates obfuscated images faithful to the original input images, and additionally increase uncertainty by 6.2$\times$ (or up to 0.85 bits) over the non-obfuscated counterparts.

Few-shot learning methods operate in low data regimes. The aim is to learn with few training examples per class. Although significant progress has been made in few-shot image classification, few-shot video recognition is relatively unexplored and methods based on 2D CNNs are unable to learn temporal information. In this work we thus develop a simple 3D CNN baseline, surpassing existing methods by a large margin. To circumvent the need of labeled examples, we propose to leverage weakly-labeled videos from a large dataset using tag retrieval followed by selecting the best clips with visual similarities, yielding further improvement. Our results saturate current 5-way benchmarks for few-shot video classification and therefore we propose a new challenging benchmark involving more classes and a mixture of classes with varying supervision.

Automatic detection of emergent leaders in small groups from nonverbal behaviour is a growing research topic in social signal processing but existing methods were evaluated on single datasets -- an unrealistic assumption for real-world applications in which systems are required to also work in settings unseen at training time. It therefore remains unclear whether current methods for emergent leadership detection generalise to similar but new settings and to which extent. To overcome this limitation, we are the first to study a cross-dataset evaluation setting for the emergent leadership detection task. We provide evaluations for within- and cross-dataset prediction using two current datasets (PAVIS and MPIIGroupInteraction), as well as an investigation on the robustness of commonly used feature channels (visual focus of attention, body pose, facial action units, speaking activity) and online prediction in the cross-dataset setting. Our evaluations show that using pose and eye contact based features, cross-dataset prediction is possible with an accuracy of 0.68, as such providing another important piece of the puzzle towards emergent leadership detection in the real world.

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.

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.

Due to the importance of zero-shot learning, i.e. classifying images where there is a lack of labeled training data, the number of proposed approaches has recently increased steadily. We argue that it is time to take a step back and to analyze the status quo of the area. The purpose of this paper is three-fold. First, given the fact that there is no agreed upon zero-shot learning benchmark, we first define a new benchmark by unifying both the evaluation protocols and data splits of publicly available datasets used for this task. This is an important contribution as published results are often not comparable and sometimes even flawed due to, e.g. pre-training on zero-shot test classes. Moreover, we propose a new zero-shot learning dataset, the Animals with Attributes 2 (AWA2) dataset which we make publicly available both in terms of image features and the images themselves. Second, we compare and analyze a significant number of the state-of-the-art methods in depth, both in the classic zero-shot setting but also in the more realistic generalized zero-shot setting. Finally, we discuss in detail the limitations of the current status of the area which can be taken as a basis for advancing it.

We present a simple yet effective method to infer detailed full human body shape from only a single photograph. Our model can infer full-body shape including face, hair, and clothing including wrinkles at interactive frame-rates. Results feature details even on parts that are occluded in the input image. Our main idea is to turn shape regression into an aligned image-to-image translation problem. The input to our method is a partial texture map of the visible region obtained from off-the-shelf methods. From a partial texture, we estimate detailed normal and vector displacement maps, which can be applied to a low-resolution smooth body model to add detail and clothing. Despite being trained purely with synthetic data, our model generalizes well to real-world photographs. Numerous results demonstrate the versatility and robustness of our method.

Internal thought refers to the process of directing attention away from a primary visual task to internal cognitive processing. Internal thought is a pervasive mental activity and closely related to primary task performance. As such, automatic detection of internal thought has significant potential for user modelling in intelligent interfaces, particularly for e-learning applications. Despite the close link between the eyes and the human mind, only a few studies have investigated vergence behaviour during internal thought and none has studied moment-to-moment detection of internal thought from gaze. While prior studies relied on long-term data analysis and required a large number of gaze characteristics, we describe a novel method that is computationally light-weight and that only requires eye vergence information that is readily available from binocular eye trackers. We further propose a novel paradigm to obtain ground truth internal thought annotations that exploits human blur perception. We evaluate our method for three increasingly challenging detection tasks: (1) during a controlled math-solving task, (2) during natural viewing of lecture videos, and (3) during daily activities, such as coding, browsing, and reading. Results from these evaluations demonstrate the performance and robustness of vergence-based detection of internal thought and, as such, open up new directions for research on interfaces that adapt to shifts of mental attention.

Recent methods to automatically calibrate stationary eye trackers were shown to effectively reduce inherent calibration distortion. However, these methods require additional information, such as mouse clicks or on-screen content. We propose the first method that only requires users' eye movements to reduce calibration distortion in the background while users naturally look at an interface. Our method exploits that calibration distortion makes straight saccade trajectories appear curved between the saccadic start and end points. We show that this curving effect is systematic and the result of distorted gaze projection plane. To mitigate calibration distortion, our method undistorts this plane by straightening saccade trajectories using image warping. We show that this approach improves over the common six-point calibration and is promising for reducing distortion. As such, it provides a non-intrusive solution to alleviating accuracy decrease of eye tracker during long-term use.

We consider general discrete Markov Random Fields(MRFs) with additional bottleneck potentials which penalize the maximum (instead of the sum) over local potential value taken by the MRF-assignment. Bottleneck potentials or analogous constructions have been considered in (i) combinatorial optimization (e.g. bottleneck shortest path problem, the minimum bottleneck spanning tree problem, bottleneck function minimization in greedoids), (ii) inverse problems with $L_{\infty}$-norm regularization, and (iii) valued constraint satisfaction on the $(\min,\max)$-pre-semirings. Bottleneck potentials for general discrete MRFs are a natural generalization of the above direction of modeling work to Maximum-A-Posteriori (MAP) inference in MRFs. To this end, we propose MRFs whose objective consists of two parts: terms that factorize according to (i) $(\min,+)$, i.e. potentials as in plain MRFs, and (ii) $(\min,\max)$, i.e. bottleneck potentials. To solve the ensuing inference problem, we propose high-quality relaxations and efficient algorithms for solving them. We empirically show efficacy of our approach on large scale seismic horizon tracking problems.

Generative Adversarial Networks (GANs) can achieve state-of-the-art sample quality in generative modelling tasks but suffer from the mode collapse problem. Variational Autoencoders (VAE) on the other hand explicitly maximize a reconstruction-based data log-likelihood forcing it to cover all modes, but suffer from poorer sample quality. Recent works have proposed hybrid VAE-GAN frameworks which integrate a GAN-based synthetic likelihood to the VAE objective to address both the mode collapse and sample quality issues, with limited success. This is because the VAE objective forces a trade-off between the data log-likelihood and divergence to the latent prior. The synthetic likelihood ratio term also shows instability during training. We propose a novel objective with a "Best-of-Many-Samples" reconstruction cost and a stable direct estimate of the synthetic likelihood. This enables our hybrid VAE-GAN framework to achieve high data log-likelihood and low divergence to the latent prior at the same time and shows significant improvement over both hybrid VAE-GANS and plain GANs in mode coverage and quality.

Automatic program correction is an active topic of research, which holds the potential of dramatically improving productivity of programmers during the software development process and correctness of software in general. Recent advances in machine learning, deep learning and NLP have rekindled the hope to eventually fully automate the process of repairing programs. A key challenge is ambiguity, as multiple codes -- or fixes -- can implement the same functionality. In addition, datasets by nature fail to capture the variance introduced by such ambiguities. Therefore, we propose a deep generative model to automatically correct programming errors by learning a distribution of potential fixes. Our model is formulated as a deep conditional variational autoencoder that samples diverse fixes for the given erroneous programs. In order to account for ambiguity and inherent lack of representative datasets, we propose a novel regularizer to encourage the model to generate diverse fixes. Our evaluations on common programming errors show for the first time the generation of diverse fixes and strong improvements over the state-of-the-art approaches by fixing up to 65% of the mistakes.

Meta-learning has been shown to be an effective strategy for few-shot learning. The key idea is to leverage a large number of similar few-shot tasks in order to meta-learn how to best initiate a (single) base-learner for novel few-shot tasks. While meta-learning how to initialize a base-learner has shown promising results, it is well known that hyperparameter settings such as the learning rate and the weighting of the regularization term are important to achieve best performance. We thus propose to also meta-learn these hyperparameters and in fact learn a time- and layer-varying scheme for learning a base-learner on novel tasks. Additionally, we propose to learn not only a single base-learner but an ensemble of several base-learners to obtain more robust results. While ensembles of learners have shown to improve performance in various settings, this is challenging for few-shot learning tasks due to the limited number of training samples. Therefore, our approach also aims to meta-learn how to effectively combine several base-learners. We conduct extensive experiments and report top performance for five-class few-shot recognition tasks on two challenging benchmarks: miniImageNet and Fewshot-CIFAR100 (FC100).

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 objects and their configurations. In this work, we consider the problem of autonomous block stacking and explore solutions to learning manipulation under physics constraints with visual perception inherent to the task. Inspired by the intuitive physics in humans, we first present an end-to-end learning-based approach to predict stability directly from appearance, contrasting a more traditional model-based approach with explicit 3D representations and physical simulation. We study the model's behavior together with an accompanied human subject test. It is then integrated into a real-world robotic system to guide the placement of a single wood block into the scene without collapsing existing tower structure. To further automate the process of consecutive blocks stacking, we present an alternative approach where the model learns the physics constraint through the interaction with the environment, bypassing the dedicated physics learning as in the former part of this work. In particular, we are interested in the type of tasks that require the agent to reach a given goal state that may be different for every new trial. Thereby we propose a deep reinforcement learning framework that learns policies for stacking tasks which are parametrized by a target structure.

Today's deep learning systems deliver high performance based on end-to-end training. While they deliver strong performance, these systems are hard to interpret. To address this issue, we propose Semantic Bottleneck Networks (SBN): deep networks with semantically interpretable intermediate layers that all downstream results are based on. As a consequence, the analysis on what the final prediction is based on is transparent to the engineer and failure cases and modes can be analyzed and avoided by high-level reasoning. We present a case study on street scene segmentation to demonstrate the feasibility and power of SBN. In particular, we start from a well performing classic deep network which we adapt to house a SB-Layer containing task related semantic concepts (such as object-parts and materials). Importantly, we can recover state of the art performance despite a drastic dimensionality reduction from 1000s (non-semantic feature) to 10s (semantic concept) channels. Additionally we show how the activations of the SB-Layer can be used for both the interpretation of failure cases of the network as well as for confidence prediction of the resulting output. For the first time, e.g., we show interpretable segmentation results for most predictions at over 99% accuracy.

Image-to-image (I2I) translation is a pixel-level mapping that requires a large number of paired training data and often suffers from the problems of high diversity and strong category bias in image scenes. In order to tackle these problems, we propose a novel BiLevel (BiL) learning paradigm that alternates the learning of two models, respectively at an instance-specific (IS) and a general-purpose (GP) level. In each scene, the IS model learns to maintain the specific scene attributes. It is initialized by the GP model that learns from all the scenes to obtain the generalizable translation knowledge. This GP initialization gives the IS model an efficient starting point, thus enabling its fast adaptation to the new scene with scarce training data. We conduct extensive I2I translation experiments on human face and street view datasets. Quantitative results validate that our approach can significantly boost the performance of classical I2I translation models, such as PG2 and Pix2Pix. Our visualization results show both higher image quality and more appropriate instance-specific details, e.g., the translated image of a person looks more like that person in terms of identity.

We present a real-time approach for multi-person 3D motion capture at over 30 fps using a single RGB camera. It operates in generic scenes and is robust to difficult occlusions both by other people and objects. Our method operates in subsequent stages. The first stage is a convolutional neural network (CNN) that estimates 2D and 3D pose features along with identity assignments for all visible joints of all individuals. We contribute a new architecture for this CNN, called SelecSLS Net, that uses novel selective long and short range skip connections to improve the information flow allowing for a drastically faster network without compromising accuracy. In the second stage, a fully-connected neural network turns the possibly partial (on account of occlusion) 2D pose and 3D pose features for each subject into a complete 3D pose estimate per individual. The third stage applies space-time skeletal model fitting to the predicted 2D and 3D pose per subject to further reconcile the 2D and 3D pose, and enforce temporal coherence. Our method returns the full skeletal pose in joint angles for each subject. This is a further key distinction from previous work that neither extracted global body positions nor joint angle results of a coherent skeleton in real time for multi-person scenes. The proposed system runs on consumer hardware at a previously unseen speed of more than 30 fps given 512x320 images as input while achieving state-of-the-art accuracy, which we will demonstrate on a range of challenging real-world scenes.

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.

Modern approaches to pose and body shape estimation have recently achieved strong performance even under challenging real-world conditions. Even from a single image of a clothed person, a realistic looking body shape can be inferred that captures a users' weight group and body shape type well. This opens up a whole spectrum of applications -- in particular in fashion -- where virtual try-on and recommendation systems can make use of these new and automatized cues. However, a realistic depiction of the undressed body is regarded highly private and therefore might not be consented by most people. Hence, we ask if the automatic extraction of such information can be effectively evaded. While adversarial perturbations have been shown to be effective for manipulating the output of machine learning models -- in particular, end-to-end deep learning approaches -- state of the art shape estimation methods are composed of multiple stages. We perform the first investigation of different strategies that can be used to effectively manipulate the automatic shape estimation while preserving the overall appearance of the original image.

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.

Adversarial training is the standard to train models robust against adversarial examples. However, especially for complex datasets, adversarial training incurs a significant loss in accuracy and is known to generalize poorly to stronger attacks, e.g., larger perturbations or other threat models. In this paper, we introduce confidence-calibrated adversarial training (CCAT) where the key idea is to enforce that the confidence on adversarial examples decays with their distance to the attacked examples. We show that CCAT preserves better the accuracy of normal training while robustness against adversarial examples is achieved via confidence thresholding, i.e., detecting adversarial examples based on their confidence. Most importantly, in strong contrast to adversarial training, the robustness of CCAT generalizes to larger perturbations and other threat models, not encountered during training. For evaluation, we extend the commonly used robust test error to our detection setting, present an adaptive attack with backtracking and allow the attacker to select, per test example, the worst-case adversarial example from multiple black- and white-box attacks. We present experimental results using $L_\infty$, $L_2$, $L_1$ and $L_0$ attacks on MNIST, SVHN and Cifar10.

While great progress has been made recently in automatic image manipulation, it has been limited to object centric images like faces or structured scene datasets. In this work, we take a step towards general scene-level image editing by developing an automatic interaction-free object removal model. Our model learns to find and remove objects from general scene images using image-level labels and unpaired data in a generative adversarial network (GAN) framework. We achieve this with two key contributions: a two-stage editor architecture consisting of a mask generator and image in-painter that co-operate to remove objects, and a novel GAN based prior for the mask generator that allows us to flexibly incorporate knowledge about object shapes. We experimentally show on two datasets that our method effectively removes a wide variety of objects using weak supervision only

Deep neural perception and control networks have become key com- ponents of self-driving vehicles. User acceptance is likely to benefit from easy- to-interpret textual explanations which allow end-users to understand what trig- gered a particular behavior. Explanations may be triggered by the neural con- troller, namely introspective explanations , or informed by the neural controller’s output, namely rationalizations . We propose a new approach to introspective ex- planations which consists of two parts. First, we use a visual (spatial) attention model to train a convolutional network end-to-end from images to the vehicle control commands, i . e ., acceleration and change of course. The controller’s at- tention identifies image regions that potentially influence the network’s output. Second, we use an attention-based video-to-text model to produce textual ex- planations of model actions. The attention maps of controller and explanation model are aligned so that explanations are grounded in the parts of the scene that mattered to the controller. We explore two approaches to attention alignment, strong- and weak-alignment. Finally, we explore a version of our model that generates rationalizations, and compare with introspective explanations on the same video segments. We evaluate these models on a novel driving dataset with ground-truth human explanations, the Berkeley DeepDrive eXplanation (BDD- X) dataset. Code is available at https://github.com/JinkyuKimUCB/explainable-deep-driving

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.

Natural language explanations of deep neural network decisions provide an intuitive way for a AI agent to articulate a reasoning process. Current textual explanations learn to discuss class discriminative features in an image. However, it is also helpful to understand which attributes might change a classification decision if present in an image (e.g., "This is not a Scarlet Tanager because it does not have black wings.") We call such textual explanations counterfactual explanations, and propose an intuitive method to generate counterfactual explanations by inspecting which evidence in an input is missing, but might contribute to a different classification decision if present in the image. To demonstrate our method we consider a fine-grained image classification task in which we take as input an image and a counterfactual class and output text which explains why the image does not belong to a counterfactual class. We then analyze our generated counterfactual explanations both qualitatively and quantitatively using proposed automatic metrics.

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.

The matching of multiple objects (e.g. shapes or images) is a fundamental problem in vision and graphics. In order to robustly handle ambiguities, noise and repetitive patterns in challenging real-world settings, it is essential to take geometric consistency between points into account. Computationally, the multi-matching problem is difficult. It can be phrased as simultaneously solving multiple (NP-hard) quadratic assignment problems (QAPs) that are coupled via cycle-consistency constraints. The main limitations of existing multi-matching methods are that they either ignore geometric consistency and thus have limited robustness, or they are restricted to small-scale problems due to their (relatively) high computational cost. We address these shortcomings by introducing a Higher-order Projected Power Iteration method, which is (i) efficient and scales to tens of thousands of points, (ii) straightforward to implement, (iii) able to incorporate geometric consistency, and (iv) guarantees cycle-consistent multi-matchings. Experimentally we show that our approach is superior to existing methods.

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.

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).

With the widespread use of machine learning (ML) techniques, ML as a service has become increasingly popular. In this setting, an ML model resides on a server and users can query the model with their data via an API. However, if the user's input is sensitive, sending it to the server is not an option. Equally, the service provider does not want to share the model by sending it to the client for protecting its intellectual property and pay-per-query business model. In this paper, we propose MLCapsule, a guarded offline deployment of machine learning as a service. MLCapsule executes the machine learning model locally on the user's client and therefore the data never leaves the client. Meanwhile, MLCapsule offers the service provider the same level of control and security of its model as the commonly used server-side execution. In addition, MLCapsule is applicable to offline applications that require local execution. Beyond protecting against direct model access, we demonstrate that MLCapsule allows for implementing defenses against advanced attacks on machine learning models such as model stealing/reverse engineering and membership inference.

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.

We propose a novel approach to jointly perform 3D object retrieval and pose estimation from monocular images.In order to make the method robust to real world scene variations in the images, e.g. texture, lighting and background,we learn an embedding space from 3D data that only includes the relevant information, namely the shape and pose.Our method can then be trained for robustness under real world scene variations without having to render a large training set simulating these variations. Our learned embedding explicitly disentangles a shape vector and a pose vector, which alleviates both pose bias for 3D shape retrieval and categorical bias for pose estimation. Having the learned disentangled embedding, we train a CNN to map the images to the embedding space, and then retrieve the closest 3D shape from the database and estimate the 6D pose of the object using the embedding vectors. Our method achieves 10.8 median error for pose estimation and 0.514 top-1-accuracy for category agnostic 3D object retrieval on the Pascal3D+ dataset. It therefore outperforms the previous state-of-the-art methods on both tasks.

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.

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.

Machine learning is transforming the world. Its application areas span privacy sensitive and security critical tasks such as human identification and self-driving cars. These applications raise privacy and security related questions that are not fully understood or answered yet: Can automatic person recognisers identify people in photos even when their faces are blurred? How easy is it to find an adversarial input for a self-driving car that makes it drive off the road? This thesis contributes one of the first steps towards a better understanding of such concerns. We observe that many privacy and security critical scenarios for learned models involve input data manipulation: users obfuscate their identity by blurring their faces and adversaries inject imperceptible perturbations to the input signal. We introduce a data manipulator framework as a tool for collectively describing and analysing privacy and security relevant scenarios involving learned models. A data manipulator introduces a shift in data distribution for achieving privacy or security related goals, and feeds the transformed input to the target model. This framework provides a common perspective on the studies presented in the thesis. We begin the studies from the user’s privacy point of view. We analyse the efficacy of common obfuscation methods like face blurring, and show that they are surprisingly ineffective against state of the art person recognition systems. We then propose alternatives based on head inpainting and adversarial examples. By studying the user privacy, we also study the dual problem: model security. In model security perspective, a model ought to be robust and reliable against small amounts of data manipulation. In both cases, data are manipulated with the goal of changing the target model prediction. User privacy and model security problems can be described with the same objective. We then study the knowledge aspect of the data manipulation problem. The more one knows about the target model, the more effective manipulations one can craft. We propose a game theoretic manipulation framework to systematically represent the knowledge level on the target model and derive privacy and security guarantees. We then discuss ways to increase knowledge about a black-box model by only querying it, deriving implications that are relevant to both privacy and security perspectives.

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.

We propose a novel end-to-end trainable framework for the graph decomposition problem. The minimum cost multicut problem is first converted to an unconstrained binary cubic formulation where cycle consistency constraints are incorporated into the objective function. The new optimization problem can be viewed as a Conditional Random Field (CRF) in which the random variables are associated with the binary edge labels of the initial graph and the hard constraints are introduced in the CRF as high-order potentials. The parameters of a standard Neural Network and the fully differentiable CRF are optimized in an end-to-end manner. Furthermore, our method utilizes the cycle constraints as meta-supervisory signals during the learning of the deep feature representations by taking the dependencies between the output random variables into account. We present analyses of the end-to-end learned representations, showing the impact of the joint training, on the task of clustering images of MNIST. We also validate the effectiveness of our approach both for the feature learning and the final clustering on the challenging task of real-world multi-person pose estimation.

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.

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.

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.

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.

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.

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.

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.

Much progress has been made in image and video segmentation over the last years. To a large extent, the success can be attributed to the strong appearance models completely learned from data, in particular using deep learning methods. However,to perform best these methods require large representative datasets for training with expensive pixel-level annotations, which in case of videos are prohibitive to obtain. Therefore, there is a need to relax this constraint and to consider alternative forms of supervision, which are easier and cheaper to collect. In this thesis, we aim to develop algorithms for learning to segment in images and videos with different levels of supervision. First, we develop approaches for training convolutional networks with weaker forms of supervision, such as bounding boxes or image labels, for object boundary estimation and semantic/instance labelling tasks. We propose to generate pixel-level approximate groundtruth from these weaker forms of annotations to train a network, which allows to achieve high-quality results comparable to the full supervision quality without any modifications of the network architecture or the training procedure. Second, we address the problem of the excessive computational and memory costs inherent to solving video segmentation via graphs. We propose approaches to improve the runtime and memory efficiency as well as the output segmentation quality by learning from the available training data the best representation of the graph. In particular, we contribute with learning must-link constraints, the topology and edge weights of the graph as well as enhancing the graph nodes - superpixels - themselves. Third, we tackle the task of pixel-level object tracking and address the problem of the limited amount of densely annotated video data for training convolutional networks. We introduce an architecture which allows training with static images only and propose an elaborate data synthesis scheme which creates a large number of training examples close to the target domain from the given first frame mask. With the proposed techniques we show that densely annotated consequent video data is not necessary to achieve high-quality temporally coherent video segmentationresults. In summary, this thesis advances the state of the art in weakly supervised image segmentation, graph-based video segmentation and pixel-level object tracking and contributes with the new ways of training convolutional networks with a limited amount of pixel-level annotated training data.

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.

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.

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.

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.

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.

Deep models are the defacto standard in visual decision problems due to their impressive performance on a wide array of visual tasks. On the other hand, their opaqueness has led to a surge of interest in explainable systems. In this work, we emphasize the importance of model explanation in various forms such as visual pointing and textual justification. The lack of data with justification annotations is one of the bottlenecks of generating multimodal explanations. Thus, we propose two large-scale datasets with annotations that visually and textually justify a classification decision for various activities, i.e. ACT-X, and for question answering, i.e. VQA-X. We also introduce a multimodal methodology for generating visual and textual explanations simultaneously. We quantitatively show that training with the textual explanations not only yields better textual justification models, but also models that better localize the evidence that support their decision.

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.

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 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.

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.

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.

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.

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.

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

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.

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.