Related papers: Versatile Ordering Network: An Attention-based Neu…

Data-driven approaches have been proven effective in solving combinatorial optimization problems over graphs such as the traveling salesman problems and the vehicle routing problem. The rationale behind such methods is that the input…

Achieving invariance to nuisance transformations is a fundamental challenge in the construction of robust and reliable vision systems. Existing approaches to invariance scale exponentially with the dimension of the family of…

Self-attention networks (SAN) have attracted a lot of interests due to their high parallelization and strong performance on a variety of NLP tasks, e.g. machine translation. Due to the lack of recurrence structure such as recurrent neural…

Convolutional Neural Networks (CNNs) have demonstrated state-of-the-art performance on many visual recognition tasks. However, the combination of convolution and pooling operations only shows invariance to small local location changes in…

We propose a novel deep visual odometry (VO) method that considers global information by selecting memory and refining poses. Existing learning-based methods take the VO task as a pure tracking problem via recovering camera poses from image…

We propose a novel approach to image classification inspired by complex nonlinear biological visual processing, whereby classical convolutional neural networks (CNNs) are equipped with learnable higher-order convolutions. Our model…

Artificial neural networks (ANNs), have become ubiquitous and revolutionized many applications ranging from computer vision to medical diagnoses. However, they offer a fundamentally connectionist and distributed approach to computing, in…

Nested dropout is a variant of dropout operation that is able to order network parameters or features based on the pre-defined importance during training. It has been explored for: I. Constructing nested nets: the nested nets are neural…

We consider the problem of Vision-and-Language Navigation (VLN). The majority of current methods for VLN are trained end-to-end using either unstructured memory such as LSTM, or using cross-modal attention over the egocentric observations…

Attention-based neural networks such as the Vision Transformer (ViT) have recently attained state-of-the-art results on many computer vision benchmarks. Scale is a primary ingredient in attaining excellent results, therefore, understanding…

Self-Organizing Map (SOM) is a neural network model which is used to obtain a topology-preserving mapping from the (usually high dimensional) input/feature space to an output/map space of fewer dimensions (usually two or three in order to…

Inventory planning for retail chains requires translating demand forecasts into ordering decisions, including asymmetric shortages and holding costs. The VN2 Inventory Planning Challenge formalizes this setting as a weekly decision-making…

This paper proposes a novel stable learning theory for recurrent neural networks (RNNs), so-called variational adaptive noise and dropout (VAND). As stabilizing factors for RNNs, noise and dropout on the internal state of RNNs have been…

Visual navigation is a fundamental problem in embodied AI, yet practical deployments demand long-horizon planning capabilities to address multi-objective tasks. A major bottleneck is data scarcity: policies learned from limited data often…

Graph vertex ordering is widely employed in spatial data analysis, especially in urban analytics, where street graphs serve as spatial discretization for modeling and simulation. It is also crucial for visualization, as many methods require…

Vision-and-Language Navigation (VLN) is unique in that it requires turning relatively general natural-language instructions into robot agent actions, on the basis of the visible environment. This requires to extract value from two very…

Various factorization-based methods have been proposed to leverage second-order, or higher-order cross features for boosting the performance of predictive models. They generally enumerate all the cross features under a predefined maximum…

We approach structured output prediction by optimizing a deep value network (DVN) to precisely estimate the task loss on different output configurations for a given input. Once the model is trained, we perform inference by gradient descent…

We propose a thermodynamics-based learning strategy for non-equilibrium evolution equations based on Onsager's variational principle, which allows to write such PDEs in terms of two potentials: the free energy and the dissipation potential.…

Deep neural networks (DNNs) are a type of artificial intelligence models that are inspired by the structure and function of the human brain, designed to process and learn from large amounts of data, making them particularly well-suited for…