Related papers: CrossViT: Cross-Attention Multi-Scale Vision Trans…

Recent Vision Transformer (ViT)-based methods for Image Super-Resolution have demonstrated impressive performance. However, they suffer from significant complexity, resulting in high inference times and memory usage. Additionally, ViT…

We present Multiscale Vision Transformers (MViT) for video and image recognition, by connecting the seminal idea of multiscale feature hierarchies with transformer models. Multiscale Transformers have several channel-resolution scale…

We propose an end-to-end image compression and analysis model with Transformers, targeting to the cloud-based image classification application. Instead of placing an existing Transformer-based image classification model directly after an…

Modern vision transformers leverage visually inspired local interaction between pixels through attention computed within window or grid regions, in contrast to the global attention employed in the original ViT. Regional attention restricts…

Vision Transformers (ViTs) have achieved remarkable success in various computer vision tasks. However, ViTs have a huge computational cost due to their inherent reliance on multi-head self-attention (MHSA), prompting efforts to accelerate…

Self-attention in Transformers comes with a high computational cost because of their quadratic computational complexity, but their effectiveness in addressing problems in language and vision has sparked extensive research aimed at enhancing…

Vision Transformer (ViT) has recently demonstrated promise in computer vision problems. However, unlike Convolutional Neural Networks (CNN), it is known that the performance of ViT saturates quickly with depth increasing, due to the…

Convolutional Neural Networks (CNNs) have dominated computer vision for years, due to its ability in capturing locality and translation invariance. Recently, many vision transformer architectures have been proposed and they show promising…

Remote sensing imagery plays a crucial role in many applications and requires accurate computerized classification techniques. Reliable classification is essential for transforming raw imagery into structured and usable information. While…

Image segmentation remains a challenging task in computer vision, demanding robust mask generation and precise classification. Recent mask-based approaches yield high-quality masks by capturing global context. However, accurately…

Transformer has been very successful in various computer vision tasks and understanding the working mechanism of transformer is important. As touchstones, weakly-supervised semantic segmentation (WSSS) and class activation map (CAM) are…

Vision Transformer (ViT) has made significant advancements in computer vision, thanks to its token mixer's sophisticated ability to capture global dependencies between all tokens. However, the quadratic growth in computational demands as…

Vision Transformers (ViTs) have become a universal backbone for both image recognition and image generation. Yet their Multi-Head Self-Attention (MHSA) layer still performs a quadratic query-key interaction for every token pair, spending…

Motivated by the success of Transformers in natural language processing (NLP) tasks, there emerge some attempts (e.g., ViT and DeiT) to apply Transformers to the vision domain. However, pure Transformer architectures often require a large…

Vision transformers have achieved significant improvements on various vision tasks but their quadratic interactions between tokens significantly reduce computational efficiency. Many pruning methods have been proposed to remove redundant…

We present in this paper a new architecture, named Convolutional vision Transformer (CvT), that improves Vision Transformer (ViT) in performance and efficiency by introducing convolutions into ViT to yield the best of both designs. This is…

Recently, the Vision Transformer (ViT), which applied the transformer structure to the image classification task, has outperformed convolutional neural networks. However, the high performance of the ViT results from pre-training using a…

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…

Recently, Transformers have emerged as the go-to architecture for both vision and language modeling tasks, but their computational efficiency is limited by the length of the input sequence. To address this, several efficient variants of…

Given a query patch from a novel class, one-shot object detection aims to detect all instances of that class in a target image through the semantic similarity comparison. However, due to the extremely limited guidance in the novel class as…