Related papers: FusionNet and AugmentedFlowNet: Selective Proxy Gr…

In order to reduce overfitting, neural networks are typically trained with data augmentation, the practice of artificially generating additional training data via label-preserving transformations of existing training examples. While these…

Rapid progress in adversarial learning has enabled the generation of realistic-looking fake visual content. To distinguish between fake and real visual content, several detection techniques have been proposed. The performance of most of…

We introduce an approach to training a given compact network. To this end, we leverage over-parameterization, which typically improves both neural network optimization and generalization. Specifically, we propose to expand each linear layer…

Artificial Neural Networks (ANNs) are increasingly deployed across diverse real-world settings, where they must operate under data distributions that differ from those seen during training. This challenge is central to Domain Generalization…

Due to data privacy issues, accelerating networks with tiny training sets has become a critical need in practice. Previous methods achieved promising results empirically by filter-level pruning. In this paper, we both study this problem…

Despite significant progress in image-based 3D scene flow estimation, the performance of such approaches has not yet reached the fidelity required by many applications. Simultaneously, these applications are often not restricted to…

Deep neural networks demonstrate to have a high performance on image classification tasks while being more difficult to train. Due to the complexity and vanishing gradient problem, it normally takes a lot of time and more computational…

It is well understood that neural networks with carefully hand-picked weights provide powerful function approximation and that they can be successfully trained in over-parametrized regimes. Since over-parametrization ensures zero training…

Learning with a primary objective, such as softmax cross entropy for classification and sequence generation, has been the norm for training deep neural networks for years. Although being a widely-adopted approach, using cross entropy as the…

Scene flow estimation is an essential ingredient for a variety of real-world applications, especially for autonomous agents, such as self-driving cars and robots. While recent scene flow estimation approaches achieve a reasonable accuracy,…

Open-set few-shot image classification aims to train models using a small amount of labeled data, enabling them to achieve good generalization when confronted with unknown environments. Existing methods mainly use visual information from a…

Computing optical flow is a fundamental problem in computer vision. However, deep learning-based optical flow techniques do not perform well for non-rigid movements such as those found in faces, primarily due to lack of the training data…

We propose an extension of Convolutional Neural Networks (CNNs) to graph-structured data, including strided convolutions and data augmentation on graphs. Our method matches the accuracy of state-of-the-art CNNs when applied on images,…

For proper generalization performance of convolutional neural networks (CNNs) in medical image segmentation, the learnt features should be invariant under particular non-linear shape variations of the input. To induce invariance in CNNs to…

Machine learning is gaining growing momentum in various recent models for the dynamic analysis of information flows in data communications networks. These preliminary models often rely on off-the-shelf learning models to predict from…

The FlowNet demonstrated that optical flow estimation can be cast as a learning problem. However, the state of the art with regard to the quality of the flow has still been defined by traditional methods. Particularly on small displacements…

While hardware-software co-design has significantly improved the efficiency of neural network inference, modeling the training phase remains a critical yet underexplored challenge. Training workloads impose distinct constraints,…

Semantic grids can be useful representations of the scene around an autonomous system. By having information about the layout of the space around itself, a robot can leverage this type of representation for crucial tasks such as navigation…

The diversity of deep learning applications, datasets, and neural network architectures necessitates a careful selection of the architecture and data that match best to a target application. As an attempt to mitigate this dilemma, this…

Alignment between image and text has shown promising improvements on patch-level pre-trained document image models. However, investigating more effective or finer-grained alignment techniques during pre-training requires a large amount of…