Related papers: Demystify Self-Attention in Vision Transformers fr…

Language and vision-language models have shown impressive performance across a wide range of tasks, but their internal mechanisms remain only partly understood. In this work, we study how individual attention heads in text-generative models…

Monocular depth estimation is a central problem in computer vision with applications in robotics, AR, and autonomous driving, yet the self-attention mechanisms that drive modern Transformer architectures remain opaque. We introduce…

Low-light image enhancement aims to improve the perception of images collected in dim environments and provide high-quality data support for image recognition tasks. When dealing with photos captured under non-uniform illumination, existing…

Recent self-supervised learning (SSL) methods have shown impressive results in learning visual representations from unlabeled images. This paper aims to improve their performance further by utilizing the architectural advantages of the…

The large adoption of the self-attention (i.e. transformer model) and BERT-like training principles has recently resulted in a number of high performing models on a large panoply of vision-and-language problems (such as Visual Question…

This paper introduces a novel attention mechanism, called dual attention, which is both efficient and effective. The dual attention mechanism consists of two parallel components: local attention generated by Convolutional Neural Networks…

We demonstrate that quantum vision transformers (QViTs), vision transformers (ViTs) with self-attention (SA) mechanisms replaced by quantum self-attention (QSA) mechanisms, can match state-of-the-art (SOTA) biomedical image classifiers…

Recently, transformers have shown great potential in image classification and established state-of-the-art results on the ImageNet benchmark. However, compared to CNNs, transformers converge slowly and are prone to overfitting in low-data…

Vision Transformers (ViTs) have redefined image classification by leveraging self-attention to capture complex patterns and long-range dependencies between image patches. However, a key challenge for ViTs is efficiently incorporating…

Neural attention, especially the self-attention made popular by the Transformer, has become the workhorse of state-of-the-art natural language processing (NLP) models. Very recent work suggests that the self-attention in the Transformer…

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…

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…

Though vision transformers (ViTs) have achieved state-of-the-art performance in a variety of settings, they exhibit surprising failures when performing tasks involving visual relations. This begs the question: how do ViTs attempt to perform…

Biomedical image classification requires capturing of bio-informatics based on specific feature distribution. In most of such applications, there are mainly challenges due to limited availability of samples for diseased cases and imbalanced…

Vision Transformers (ViTs) have shown impressive performance but still require a high computation cost as compared to convolutional neural networks (CNNs), one reason is that ViTs' attention measures global similarities and thus has a…

Although transformers have become the neural architectures of choice for natural language processing, they require orders of magnitude more training data, GPU memory, and computations in order to compete with convolutional neural networks…

Transformers have recently shown superior performances on various vision tasks. The large, sometimes even global, receptive field endows Transformer models with higher representation power over their CNN counterparts. Nevertheless, simply…

Textual cues are essential for everyday tasks like buying groceries and using public transport. To develop this assistive technology, we study the TextVQA task, i.e., reasoning about text in images to answer a question. Existing approaches…

Image Restoration (IR), a classic low-level vision task, has witnessed significant advancements through deep models that effectively model global information. Notably, the emergence of Vision Transformers (ViTs) has further propelled these…

Transformers have achieved widespread success in computer vision. At their heart, there is a Self-Attention (SA) mechanism, an inductive bias that associates each token in the input with every other token through a weighted basis. The…