English
Related papers

Related papers: Discrete Representations Strengthen Vision Transfo…

200 papers

Multi-scale Vision Transformer (ViT) has emerged as a powerful backbone for computer vision tasks, while the self-attention computation in Transformer scales quadratically w.r.t. the input patch number. Thus, existing solutions commonly…

Computer Vision and Pattern Recognition · Computer Science 2022-07-12 Ting Yao , Yingwei Pan , Yehao Li , Chong-Wah Ngo , Tao Mei

ViTs are general and accurate, and address many tasks, but ViTs are slow, and are not always practical when efficiency is key. Existing methods for faster ViTs design hybrid non-ViT architectures, losing generality, or shrink their tokens,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Anthony Fuller , Yousef Yassin , Daniel G. Kyrollos , Evan Shelhamer , James R. Green

Attention is sparse in vision transformers. We observe the final prediction in vision transformers is only based on a subset of most informative tokens, which is sufficient for accurate image recognition. Based on this observation, we…

Computer Vision and Pattern Recognition · Computer Science 2021-10-27 Yongming Rao , Wenliang Zhao , Benlin Liu , Jiwen Lu , Jie Zhou , Cho-Jui Hsieh

Vision Transformers (ViTs) have shown impressive performance in computer vision, but their high computational cost, quadratic in the number of tokens, limits their adoption in computation-constrained applications. However, this large number…

Computer Vision and Pattern Recognition · Computer Science 2023-12-14 Yifei Liu , Mathias Gehrig , Nico Messikommer , Marco Cannici , Davide Scaramuzza

Vision Transformers (ViTs) have achieved comparable or superior performance than Convolutional Neural Networks (CNNs) in computer vision. This empirical breakthrough is even more remarkable since, in contrast to CNNs, ViTs do not embed any…

Computer Vision and Pattern Recognition · Computer Science 2022-10-18 Samy Jelassi , Michael E. Sander , Yuanzhi Li

Vision Transformers (ViTs) have emerged as powerful models in the field of computer vision, delivering superior performance across various vision tasks. However, the high computational complexity poses a significant barrier to their…

Computer Vision and Pattern Recognition · Computer Science 2024-02-06 Xinjian Wu , Fanhu Zeng , Xiudong Wang , Xinghao Chen

Deep neural networks may be susceptible to learning spurious correlations that hold on average but not in atypical test samples. As with the recent emergence of vision transformer (ViT) models, it remains underexplored how spurious…

Computer Vision and Pattern Recognition · Computer Science 2022-03-18 Soumya Suvra Ghosal , Yifei Ming , Yixuan Li

With the success of Vision Transformers (ViTs) in computer vision tasks, recent arts try to optimize the performance and complexity of ViTs to enable efficient deployment on mobile devices. Multiple approaches are proposed to accelerate…

Computer Vision and Pattern Recognition · Computer Science 2023-09-06 Yanyu Li , Ju Hu , Yang Wen , Georgios Evangelidis , Kamyar Salahi , Yanzhi Wang , Sergey Tulyakov , Jian Ren

Vision Transformers (ViTs) have achieved state-of-the-art performance in image classification, yet their attention mechanisms often remain opaque and exhibit dense, non-structured behaviors. In this work, we adapt our previously proposed…

Computer Vision and Pattern Recognition · Computer Science 2026-02-12 Vasileios Arampatzakis , George Pavlidis , Nikolaos Mitianoudis , Nikos Papamarkos

The ubiquitous and demonstrably suboptimal choice of resizing images to a fixed resolution before processing them with computer vision models has not yet been successfully challenged. However, models such as the Vision Transformer (ViT)…

Computer vision has achieved remarkable success by (a) representing images as uniformly-arranged pixel arrays and (b) convolving highly-localized features. However, convolutions treat all image pixels equally regardless of importance;…

Computer Vision and Pattern Recognition · Computer Science 2020-11-23 Bichen Wu , Chenfeng Xu , Xiaoliang Dai , Alvin Wan , Peizhao Zhang , Zhicheng Yan , Masayoshi Tomizuka , Joseph Gonzalez , Kurt Keutzer , Peter Vajda

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

Vision Transformers naturally accommodate sparsity, yet standard tokenization methods confine features to discrete patch grids. This constraint prevents models from fully exploiting sparse regimes, forcing awkward compromises. We propose…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Martine Hjelkrem-Tan , Marius Aasan , Gabriel Y. Arteaga , Adín Ramírez Rivera

Vision Transformers (ViTs) are known to exhibit high-norm patch-token outliers that degrade feature map quality, a problem effectively mitigated by \textit{register tokens}. As diffusion models increasingly adopt transformer architectures…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Nikita Starodubcev , Ilia Sudakov , Ilya Drobyshevskiy , Artem Babenko , Dmitry Baranchuk

The recently proposed Visual image Transformers (ViT) with pure attention have achieved promising performance on image recognition tasks, such as image classification. However, the routine of the current ViT model is to maintain a…

Computer Vision and Pattern Recognition · Computer Science 2021-08-19 Zizheng Pan , Bohan Zhuang , Jing Liu , Haoyu He , Jianfei Cai

We propose Vision Token Turing Machines (ViTTM), an efficient, low-latency, memory-augmented Vision Transformer (ViT). Our approach builds on Neural Turing Machines and Token Turing Machines, which were applied to NLP and sequential visual…

Computer Vision and Pattern Recognition · Computer Science 2025-01-27 Purvish Jajal , Nick John Eliopoulos , Benjamin Shiue-Hal Chou , George K. Thiruvathukal , James C. Davis , Yung-Hsiang Lu

Vision Transformers (ViTs) have achieved overwhelming success, yet they suffer from vulnerable resolution scalability, i.e., the performance drops drastically when presented with input resolutions that are unseen during training. We…

Computer Vision and Pattern Recognition · Computer Science 2023-04-04 Rui Tian , Zuxuan Wu , Qi Dai , Han Hu , Yu Qiao , Yu-Gang Jiang

Deep learning technology can be used as an assistive technology to help doctors quickly and accurately identify COVID-19 infections. Recently, Vision Transformer (ViT) has shown great potential towards image classification due to its global…

Image and Video Processing · Electrical Eng. & Systems 2022-07-06 Hongyan Xu , Xiu Su , Dadong Wang

Semantic segmentation has a broad range of applications in a variety of domains including land coverage analysis, autonomous driving, and medical image analysis. Convolutional neural networks (CNN) and Vision Transformers (ViTs) provide the…

Computer Vision and Pattern Recognition · Computer Science 2023-05-08 Hans Thisanke , Chamli Deshan , Kavindu Chamith , Sachith Seneviratne , Rajith Vidanaarachchi , Damayanthi Herath

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