Related papers: Visual Attention Emerges from Recurrent Sparse Rec…
In this work, we aim to predict human eye fixation with view-free scenes based on an end-to-end deep learning architecture. Although Convolutional Neural Networks (CNNs) have made substantial improvement on human attention prediction, it is…
While CNNs naturally lend themselves to densely sampled data, and sophisticated implementations are available, they lack the ability to efficiently process sparse data. In this work we introduce a suite of tools that exploit sparsity in…
Human visual recognition is a sparse process, where only a few salient visual cues are attended to rather than traversing every detail uniformly. However, most current vision networks follow a dense paradigm, processing every single visual…
We present an attention-based modular neural framework for computer vision. The framework uses a soft attention mechanism allowing models to be trained with gradient descent. It consists of three modules: a recurrent attention module…
Attention-based graph neural networks have made great progress in feature matching learning. However, insight of how attention mechanism works for feature matching is lacked in the literature. In this paper, we rethink cross- and…
Scaling video diffusion transformers (DiTs) is limited by their quadratic 3D attention, even though most of the attention mass concentrates on a small subset of positions. We turn this observation into VSA, a trainable, hardware-efficient…
Vision transformers (ViT) have been of broad interest in recent theoretical and empirical works. They are state-of-the-art thanks to their attention-based approach, which boosts the identification of key features and patterns within images…
Recently, it has been argued that encoder-decoder models can be made more interpretable by replacing the softmax function in the attention with its sparse variants. In this work, we introduce a novel, simple method for achieving sparsity in…
Vision transformers (ViTs) have been successfully applied in image classification tasks recently. In this paper, we show that, unlike convolution neural networks (CNNs)that can be improved by stacking more convolutional layers, the…
Deep neural networks, including recurrent networks, have been successfully applied to human activity recognition. Unfortunately, the final representation learned by recurrent networks might encode some noise (irrelevant signal components,…
The recent neural surface reconstruction by volume rendering approaches have made much progress by achieving impressive surface reconstruction quality, but are still limited to dense and highly accurate posed views. To overcome such…
Binary determination of the presence of objects is one of the problems where humans perform extraordinarily better than computer vision systems, in terms of both speed and preciseness. One of the possible reasons is that humans can skip…
Modeling multivariate time series as temporal signals over a (possibly dynamic) graph is an effective representational framework that allows for developing models for time series analysis. In fact, discrete sequences of graphs can be…
While inference-time scaling has significantly enhanced generative quality in large language and diffusion models, its application to vector-quantized (VQ) visual autoregressive modeling (VAR) remains unexplored. We introduce VAR-Scaling,…
Scaling Diffusion Transformers to generate high-resolution, long videos is constrained by the quadratic cost of self-attention, and existing sparse attention methods degrade under high sparsity. We show empirically that generation quality…
Convolution has been arguably the most important feature transform for modern neural networks, leading to the advance of deep learning. Recent emergence of Transformer networks, which replace convolution layers with self-attention blocks,…
Visual Commonsense Reasoning (VCR) remains a significant yet challenging research problem in the realm of visual reasoning. A VCR model generally aims at answering a textual question regarding an image, followed by the rationale prediction…
Autoregressive (AR) transformers have emerged as a powerful paradigm for visual generation, largely due to their scalability, computational efficiency and unified architecture with language and vision. Among them, next scale prediction…
While artificial neural networks excel in unsupervised learning of non-sparse structure, classical statistical regression techniques offer better interpretability, in particular when sparseness is enforced by $\ell_1$ regularization,…
Self-attention based Transformer has demonstrated the state-of-the-art performances in a number of natural language processing tasks. Self-attention is able to model long-term dependencies, but it may suffer from the extraction of…