Related papers: Top-Down Visual Attention from Analysis by Synthes…
Vision transformers (ViTs) achieve remarkable performance on large datasets, but tend to perform worse than convolutional neural networks (CNNs) when trained from scratch on smaller datasets, possibly due to a lack of local inductive bias…
Vision Transformers have witnessed prevailing success in a series of vision tasks. However, these Transformers often rely on extensive computational costs to achieve high performance, which is burdensome to deploy on resource-constrained…
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…
Vision Transformers (ViTs) have been shown to enhance visual recognition through modeling long-range dependencies with multi-head self-attention (MHSA), which is typically formulated as Query-Key-Value computation. However, the attention…
Findings in recent years on the sensitivity of convolutional neural networks to additive noise, light conditions and to the wholeness of the training dataset, indicate that this technology still lacks the robustness needed for the…
Vision Transformer (ViT) has gained increasing attention in the computer vision community in recent years. However, the core component of ViT, Self-Attention, lacks explicit spatial priors and bears a quadratic computational complexity,…
Attention-based transformer networks have demonstrated promising potential as their applications extend from natural language processing to vision. However, despite the recent improvements, such as sub-quadratic attention approximation and…
Transformer-based methods have shown impressive performance in image restoration tasks, such as image super-resolution and denoising. However, we find that these networks can only utilize a limited spatial range of input information through…
In this paper a pure-attention bottom-up approach, called ViGAT, that utilizes an object detector together with a Vision Transformer (ViT) backbone network to derive object and frame features, and a head network to process these features…
Vision transformers using self-attention or its proposed alternatives have demonstrated promising results in many image related tasks. However, the underpinning inductive bias of attention is not well understood. To address this issue, this…
Vision Transformers (ViTs) are built on the assumption of treating image patches as ``visual tokens" and learn patch-to-patch attention. The patch embedding based tokenizer has a semantic gap with respect to its counterpart, the textual…
Vision transformers (ViT) rely on attention mechanism to weigh input features, and therefore attention scores have naturally been considered as explanations for its decision-making process. However, attention scores are almost always…
Vision Transformers (ViTs) have become prominent models for solving various vision tasks. However, the interpretability of ViTs has not kept pace with their promising performance. While there has been a surge of interest in developing {\it…
Visual explanation (attention)-guided learning uses not only labels but also explanations to guide model reasoning process. While visual attention-guided learning has shown promising results, it requires a large number of explanation…
Vision Transformers (ViTs), when pre-trained on large-scale data, provide general-purpose representations for diverse downstream tasks. However, artifacts in ViTs are widely observed across different supervision paradigms and downstream…
State-of-the-art sparse attention methods for reducing decoding latency fall into two main categories: approximate top-$k$ (and its extension, top-$p$) and recently introduced sampling-based estimation. However, these approaches are…
Transformers have shown superior performance on various vision tasks. Their large receptive field endows Transformer models with higher representation power than their CNN counterparts. Nevertheless, simply enlarging the receptive field…
Deep Learning has seen an unprecedented increase in vision applications since the publication of large-scale object recognition datasets and introduction of scalable compute hardware. State-of-the-art methods for most vision tasks for…
The success of Vision Transformer (ViT) has been widely reported on a wide range of image recognition tasks. ViT can learn global dependencies superior to CNN, yet CNN's inherent locality can substitute for expensive training resources.…
The favorable performance of Vision Transformers (ViTs) is often attributed to the multi-head self-attention (MSA). The MSA enables global interactions at each layer of a ViT model, which is a contrasting feature against Convolutional…