English
Related papers

Related papers: Thicker and Quicker: A Jumbo Token for Fast Plain …

200 papers

The remarkable performance of Vision Transformers (ViTs) typically requires an extremely large training cost. Existing methods have attempted to accelerate the training of ViTs, yet typically disregard method universality with accuracy…

Machine Learning · Computer Science 2024-04-02 Wenxuan Huang , Yunhang Shen , Jiao Xie , Baochang Zhang , Gaoqi He , Ke Li , Xing Sun , Shaohui Lin

Recently, plain vision Transformers (ViTs) have shown impressive performance on various computer vision tasks, thanks to their strong modeling capacity and large-scale pretraining. However, they have not yet conquered the problem of image…

Computer Vision and Pattern Recognition · Computer Science 2023-06-01 Jingfeng Yao , Xinggang Wang , Shusheng Yang , Baoyuan Wang

Vision transformers (ViTs) have emerged as a prevalent architecture for vision tasks owing to their impressive performance. However, when it comes to handling long token sequences, especially in dense prediction tasks that require…

Computer Vision and Pattern Recognition · Computer Science 2023-11-03 Jin Li , Yaoming Wang , Xiaopeng Zhang , Bowen Shi , Dongsheng Jiang , Chenglin Li , Wenrui Dai , Hongkai Xiong , Qi Tian

Although vision transformers (ViTs) have shown promising results in various computer vision tasks recently, their high computational cost limits their practical applications. Previous approaches that prune redundant tokens have demonstrated…

Computer Vision and Pattern Recognition · Computer Science 2023-04-24 Siyuan Wei , Tianzhu Ye , Shen Zhang , Yao Tang , Jiajun Liang

Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) have led to significant progress in 2D body pose estimation. However, achieving a good balance between accuracy, efficiency, and robustness remains a challenge. For…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Kaleab A. Kinfu , René Vidal

Since its inception, Vision Transformer (ViT) has emerged as a prevalent model in the computer vision domain. Nonetheless, the multi-head self-attention (MHSA) mechanism in ViT is computationally expensive due to its calculation of…

Computer Vision and Pattern Recognition · Computer Science 2023-07-25 Zhe Bian , Zhe Wang , Wenqiang Han , Kangping Wang

We introduce A-ViT, a method that adaptively adjusts the inference cost of vision transformer (ViT) for images of different complexity. A-ViT achieves this by automatically reducing the number of tokens in vision transformers that are…

Computer Vision and Pattern Recognition · Computer Science 2022-10-10 Hongxu Yin , Arash Vahdat , Jose Alvarez , Arun Mallya , Jan Kautz , Pavlo Molchanov

Vision Transformers (ViTs) have achieved remarkable performance in various image classification tasks by leveraging the attention mechanism to process image patches as tokens. However, the high computational and memory demands of ViTs pose…

Computer Vision and Pattern Recognition · Computer Science 2024-06-27 Zhengqing Yuan , Rong Zhou , Hongyi Wang , Lifang He , Yanfang Ye , Lichao Sun

Following the success in advancing natural language processing and understanding, transformers are expected to bring revolutionary changes to computer vision. This work provides a comprehensive study on the robustness of vision transformers…

Computer Vision and Pattern Recognition · Computer Science 2022-11-04 Rulin Shao , Zhouxing Shi , Jinfeng Yi , Pin-Yu Chen , Cho-Jui Hsieh

Vision Transformers (ViTs) have demonstrated outstanding performance in computer vision tasks, yet their high computational complexity prevents their deployment in computing resource-constrained environments. Various token pruning…

Computer Vision and Pattern Recognition · Computer Science 2023-11-07 Xuwei Xu , Changlin Li , Yudong Chen , Xiaojun Chang , Jiajun Liu , Sen Wang

Over the past few years, vision transformers (ViTs) have consistently demonstrated remarkable performance across various visual recognition tasks. However, attempts to enhance their robustness have yielded limited success, mainly focusing…

Computer Vision and Pattern Recognition · Computer Science 2024-10-01 Nick Nikzad , Yi Liao , Yongsheng Gao , Jun Zhou

Vision Transformer (ViT) has achieved remarkable success due to its large-scale pretraining on general domains, but it still faces challenges when applying it to downstream distant domains that have only scarce training data, which gives…

Computer Vision and Pattern Recognition · Computer Science 2025-06-04 Shuai Yi , Yixiong Zou , Yuhua Li , Ruixuan Li

Vision Transformers (ViTs) have achieved state-of-the-art performance on various vision tasks. However, ViTs' self-attention module is still arguably a major bottleneck, limiting their achievable hardware efficiency. Meanwhile, existing…

Machine Learning · Computer Science 2025-03-04 Haoran You , Zhanyi Sun , Huihong Shi , Zhongzhi Yu , Yang Zhao , Yongan Zhang , Chaojian Li , Baopu Li , Yingyan Celine Lin

With Vision Transformers (ViTs) making great advances in a variety of computer vision tasks, recent literature have proposed various variants of vanilla ViTs to achieve better efficiency and efficacy. However, it remains unclear how their…

Computer Vision and Pattern Recognition · Computer Science 2022-08-22 Rui Tian , Zuxuan Wu , Qi Dai , Han Hu , Yu-Gang Jiang

Recently, vision transformer (ViT) and its variants have achieved promising performances in various computer vision tasks. Yet the high computational costs and training data requirements of ViTs limit their application in…

Computer Vision and Pattern Recognition · Computer Science 2021-12-01 Hao Yu , Jianxin Wu

We investigate the robustness of vision transformers (ViTs) through the lens of their special patch-based architectural structure, i.e., they process an image as a sequence of image patches. We find that ViTs are surprisingly insensitive to…

Machine Learning · Computer Science 2023-02-23 Yao Qin , Chiyuan Zhang , Ting Chen , Balaji Lakshminarayanan , Alex Beutel , Xuezhi Wang

This paper studies how to keep a vision backbone effective while removing token mixers in its basic building blocks. Token mixers, as self-attention for vision transformers (ViTs), are intended to perform information communication between…

Computer Vision and Pattern Recognition · Computer Science 2023-04-13 Jiahao Wang , Songyang Zhang , Yong Liu , Taiqiang Wu , Yujiu Yang , Xihui Liu , Kai Chen , Ping Luo , Dahua Lin

Vision Transformers (ViTs) achieve state-of-the-art performance in semantic segmentation but are hindered by high computational and memory costs. To address this, we propose STEP (SuperToken and Early-Pruning), a hybrid token-reduction…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Michal Szczepanski , Martyna Poreba , Karim Haroun

Vision Transformers (ViTs) have demonstrated remarkable success on large-scale datasets, but their performance on smaller datasets often falls short of convolutional neural networks (CNNs). This paper explores the design and optimization of…

Machine Learning · Computer Science 2025-01-14 Gent Wu

While vision transformers (ViTs) have continuously achieved new milestones in the field of computer vision, their sophisticated network architectures with high computation and memory costs have impeded their deployment on resource-limited…

Hardware Architecture · Computer Science 2023-02-28 Peiyan Dong , Mengshu Sun , Alec Lu , Yanyue Xie , Kenneth Liu , Zhenglun Kong , Xin Meng , Zhengang Li , Xue Lin , Zhenman Fang , Yanzhi Wang