Related papers: ViTAEv2: Vision Transformer Advanced by Exploring …

Transformers have shown great potential in various computer vision tasks owing to their strong capability in modeling long-range dependency using the self-attention mechanism. Nevertheless, vision transformers treat an image as 1D sequence…

Vision Transformer (ViT), a radically different architecture than convolutional neural networks offers multiple advantages including design simplicity, robustness and state-of-the-art performance on many vision tasks. However, in contrast…

Visual Question Answering (VQA) has recently emerged as a potential research domain, captivating the interest of many in the field of artificial intelligence and computer vision. Despite the prevalence of approaches in English, there is 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…

In recent years, Transformer-based architectures have become the dominant method for Computer Vision applications. While Transformers are explainable and scale well with dataset size, they lack the inductive biases of Convolutional Neural…

Vision Transformers (ViT) become widely-adopted architectures for various vision tasks. Masked auto-encoding for feature pretraining and multi-scale hybrid convolution-transformer architectures can further unleash the potentials of ViT,…

Vision transformers are nowadays the de-facto choice for image classification tasks. There are two broad categories of classification tasks, fine-grained and coarse-grained. In fine-grained classification, the necessity is to discover…

Existing computer vision research in categorization struggles with fine-grained attributes recognition due to the inherently high intra-class variances and low inter-class variances. SOTA methods tackle this challenge by locating the most…

Current researches indicate that inductive bias (IB) can improve Vision Transformer (ViT) performance. However, they introduce a pyramid structure concurrently to counteract the incremental FLOPs and parameters caused by introducing IB.…

The Vision Transformer (ViT) leverages the Transformer's encoder to capture global information by dividing images into patches and achieves superior performance across various computer vision tasks. However, the self-attention mechanism of…

Self-supervised learning has attracted increasing attention as it learns data-driven representation from data without annotations. Vision transformer-based autoencoder (ViT-AE) by He et al. (2021) is a recent self-supervised learning…

Transformers, composed of multiple self-attention layers, hold strong promises toward a generic learning primitive applicable to different data modalities, including the recent breakthroughs in computer vision achieving state-of-the-art…

Vision transformers have attracted much attention from computer vision researchers as they are not restricted to the spatial inductive bias of ConvNets. However, although Transformer-based backbones have achieved much progress on ImageNet…

Image Classification is a fundamental task in the field of computer vision that frequently serves as a benchmark for gauging advancements in Computer Vision. Over the past few years, significant progress has been made in image…

Transformer, first applied to the field of natural language processing, is a type of deep neural network mainly based on the self-attention mechanism. Thanks to its strong representation capabilities, researchers are looking at ways to…

The brain interprets visual information through learned regularities, a computation formalized as probabilistic inference under a prior. The visual cortex establishes priors for this inference, some delivered through established top-down…

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…

Many animals and humans process the visual field with a varying spatial resolution (foveated vision) and use peripheral processing to make eye movements and point the fovea to acquire high-resolution information about objects of interest.…

Vision-language pre-training (VLP) on large-scale image-text pairs has achieved huge success for the cross-modal downstream tasks. The most existing pre-training methods mainly adopt a two-step training procedure, which firstly employs a…

In the last decade, convolutional neural networks (ConvNets) have dominated and achieved state-of-the-art performances in a variety of medical imaging applications. However, the performances of ConvNets are still limited by lacking the…