Prediction of trajectories such as that of pedestrians is crucial to the performance of autonomous agents. While previous works have leveraged conditional generative models like GANs and VAEs for learning the likely future trajectories, accurately modeling the dependency structure of these multimodal distributions, particularly over long time horizons remains challenging. Normalizing flow based generative models can model complex distributions admitting exact inference. These include variants with split coupling invertible transformations that are easier to parallelize compared to their autoregressive counterparts. To this end, we introduce a novel Haar wavelet based block autoregressive model leveraging split couplings, conditioned on coarse trajectories obtained from Haar wavelet based transformations at different levels of granularity. This yields an exact inference method that models trajectories at different spatio-temporal resolutions in a hierarchical manner. We illustrate the advantages of our approach for generating diverse and accurate trajectories on two real-world datasets - Stanford Drone and Intersection Drone.

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.

Intuitively, image classification should profit from using spatial information. Recent work, however, suggests that this might be overrated in standard CNNs. In this paper, we are pushing the envelope and aim to further investigate the reliance on spatial information. We propose spatial shuffling and GAP+FC to destroy spatial information during both training and testing phases. Interestingly, we observe that spatial information can be deleted from later layers with small performance drops, which indicates spatial information at later layers is not necessary for good performance. For example, test accuracy of VGG-16 only drops by 0.03% and 2.66% with spatial information completely removed from the last 30% and 53% layers on CIFAR100, respectively. Evaluation on several object recognition datasets (CIFAR100, Small-ImageNet, ImageNet) with a wide range of CNN architectures (VGG16, ResNet50, ResNet152) shows an overall consistent pattern.

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.

Class-Incremental Learning (CIL) aims to learn a classification model with the number of classes increasing phase-by-phase. The inherent problem in CIL is the stability-plasticity dilemma between the learning of old and new classes, i.e., high-plasticity models easily forget old classes but high-stability models are weak to learn new classes. We alleviate this issue by proposing a novel network architecture called Meta-Aggregating Networks (MANets) in which we explicitly build two residual blocks at each residual level (taking ResNet as the baseline architecture): a stable block and a plastic block. We aggregate the output feature maps from these two blocks and then feed the results to the next-level blocks. We meta-learn the aggregating weights in order to dynamically optimize and balance between two types of blocks, i.e., between stability and plasticity. We conduct extensive experiments on three CIL benchmarks: CIFAR-100, ImageNet-Subset, and ImageNet, and show that many existing CIL methods can be straightforwardly incorporated on the architecture of MANets to boost their performance.

Neural rendering techniques combining machine learning with geometric reasoning have arisen as one of the most promising approaches for synthesizing novel views of a scene from a sparse set of images. Among these, stands out the Neural radiance fields (NeRF), which trains a deep network to map 5D input coordinates (representing spatial location and viewing direction) into a volume density and view-dependent emitted radiance. However, despite achieving an unprecedented level of photorealism on the generated images, NeRF is only applicable to static scenes, where the same spatial location can be queried from different images. In this paper we introduce D-NeRF, a method that extends neural radiance fields to a dynamic domain, allowing to reconstruct and render novel images of objects under rigid and non-rigid motions from a \emph{single} camera moving around the scene. For this purpose we consider time as an additional input to the system, and split the learning process in two main stages: one that encodes the scene into a canonical space and another that maps this canonical representation into the deformed scene at a particular time. Both mappings are simultaneously learned using fully-connected networks. Once the networks are trained, D-NeRF can render novel images, controlling both the camera view and the time variable, and thus, the object movement. We demonstrate the effectiveness of our approach on scenes with objects under rigid, articulated and non-rigid motions. Code, model weights and the dynamic scenes dataset will be released.

Deep neural networks have been shown to be susceptible to adversarial examples -- small, imperceptible changes constructed to cause mis-classification in otherwise highly accurate image classifiers. As a practical alternative, recent work proposed so-called adversarial patches: clearly visible, but adversarially crafted rectangular patches in images. These patches can easily be printed and applied in the physical world. While defenses against imperceptible adversarial examples have been studied extensively, robustness against adversarial patches is poorly understood. In this work, we first devise a practical approach to obtain adversarial patches while actively optimizing their location within the image. Then, we apply adversarial training on these location-optimized adversarial patches and demonstrate significantly improved robustness on CIFAR10 and GTSRB. Additionally, in contrast to adversarial training on imperceptible adversarial examples, our adversarial patch training does not reduce accuracy.

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.