English
Related papers

Related papers: ThinkingViT: Matryoshka Thinking Vision Transforme…

200 papers

Vision Transformer (ViT) has emerged as a competitive alternative to convolutional neural networks for various computer vision applications. Specifically, ViT multi-head attention layers make it possible to embed information globally across…

Computer Vision and Pattern Recognition · Computer Science 2022-11-10 Jyotikrishna Dass , Shang Wu , Huihong Shi , Chaojian Li , Zhifan Ye , Zhongfeng Wang , Yingyan Lin

Vision transformers (ViT) usually extract features via forwarding all the tokens in the self-attention layers from top to toe. In this paper, we introduce dynamic token-pass vision transformers (DoViT) for semantic segmentation, which can…

Computer Vision and Pattern Recognition · Computer Science 2023-08-25 Yuang Liu , Qiang Zhou , Jing Wang , Fan Wang , Jun Wang , Wei Zhang

Vision Transformers (ViTs) have emerged as a state-of-the-art solution for object classification tasks. However, their computational demands and high parameter count make them unsuitable for real-time inference, prompting the need for…

Image and Video Processing · Electrical Eng. & Systems 2024-02-16 Kyle Marino , Pengmiao Zhang , Viktor Prasanna

Large pretrained plain vision Transformers (ViTs) have been the workhorse for many downstream tasks. However, existing works utilizing off-the-shelf ViTs are inefficient in terms of training and deployment, because adopting ViTs with…

Computer Vision and Pattern Recognition · Computer Science 2023-11-29 Zizheng Pan , Jing Liu , Haoyu He , Jianfei Cai , Bohan Zhuang

Vision Transformers (ViTs) have achieved state-of-the-art performance for various vision tasks. One reason behind the success lies in their ability to provide plausible innate explanations for the behavior of neural architectures. However,…

Computer Vision and Pattern Recognition · Computer Science 2024-05-06 Lijie Hu , Yixin Liu , Ninghao Liu , Mengdi Huai , Lichao Sun , Di Wang

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

The Vision Transformer (ViT) architecture has emerged as the backbone of choice for state-of-the-art deep models for computer vision applications. However, ViTs are ill-suited for private inference using secure multi-party computation (MPC)…

Cryptography and Security · Computer Science 2023-10-10 Naren Dhyani , Jianqiao Mo , Minsu Cho , Ameya Joshi , Siddharth Garg , Brandon Reagen , Chinmay Hegde

While current Vision Transformer (ViT) adapter methods have shown promising accuracy, their inference speed is implicitly hindered by inefficient memory access operations, e.g., standard normalization and frequent reshaping. In this work,…

Computer Vision and Pattern Recognition · Computer Science 2025-02-05 Dong Zhang , Rui Yan , Pingcheng Dong , Kwang-Ting Cheng

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

Vision Transformers (ViTs) have emerged as state-of-the-art models for various vision tasks recently. However, their heavy computation costs remain daunting for resource-limited devices. To address this, researchers have dedicated…

Computer Vision and Pattern Recognition · Computer Science 2025-10-20 Ao Wang , Hui Chen , Zijia Lin , Sicheng Zhao , Jungong Han , Guiguang Ding

Vision transformer (ViT) models exhibit substandard optimizability. In particular, they are sensitive to the choice of optimizer (AdamW vs. SGD), optimizer hyperparameters, and training schedule length. In comparison, modern convolutional…

Computer Vision and Pattern Recognition · Computer Science 2021-10-27 Tete Xiao , Mannat Singh , Eric Mintun , Trevor Darrell , Piotr Dollár , Ross Girshick

The advent of Vision Transformers (ViTs) marks a substantial paradigm shift in the realm of computer vision. ViTs capture the global information of images through self-attention modules, which perform dot product computations among…

Computer Vision and Pattern Recognition · Computer Science 2024-06-04 Shuoxi Zhang , Hanpeng Liu , Stephen Lin , Kun He

Vision Transformer (ViT) has gained increasing attention in the computer vision community in recent years. However, the core component of ViT, Self-Attention, lacks explicit spatial priors and bears a quadratic computational complexity,…

Computer Vision and Pattern Recognition · Computer Science 2025-02-28 Qihang Fan , Huaibo Huang , Mingrui Chen , Hongmin Liu , Ran He

The large pre-trained vision transformers (ViTs) have demonstrated remarkable performance on various visual tasks, but suffer from expensive computational and memory cost problems when deployed on resource-constrained devices. Among the…

Computer Vision and Pattern Recognition · Computer Science 2022-10-14 Yanjing Li , Sheng Xu , Baochang Zhang , Xianbin Cao , Peng Gao , Guodong Guo

The attention module in vision transformers(ViTs) performs intricate spatial correlations, contributing significantly to accuracy and delay. It is thereby important to modulate the number of attentions according to the input feature…

Hardware Architecture · Computer Science 2024-04-24 Abhishek Moitra , Abhiroop Bhattacharjee , Priyadarshini Panda

Recent state-of-the-art performances of Vision Transformers (ViT) in computer vision tasks demonstrate that a general-purpose architecture, which implements long-range self-attention, could replace the local feature learning operations of…

Test-Time Training (TTT) has recently emerged as a promising direction for efficient sequence modeling. TTT reformulates attention operation as an online learning problem, constructing a compact inner model from key-value pairs at test…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Dongchen Han , Yining Li , Tianyu Li , Zixuan Cao , Ziming Wang , Jun Song , Yu Cheng , Bo Zheng , Gao Huang

Vision Transformers (ViTs) have emerged as a powerful architecture for computer vision tasks due to their ability to model long-range dependencies and global contextual relationships. However, their substantial compute and memory demands…

Vision Transformer models, such as ViT, Swin Transformer, and Transformer-in-Transformer, have recently gained significant traction in computer vision tasks due to their ability to capture the global relation between features which leads to…

Hardware Architecture · Computer Science 2023-09-13 Shashank Nag , Gourav Datta , Souvik Kundu , Nitin Chandrachoodan , Peter A. Beerel

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…

Computer Vision and Pattern Recognition · Computer Science 2023-05-16 Ibrahim Batuhan Akkaya , Senthilkumar S. Kathiresan , Elahe Arani , Bahram Zonooz