English
Related papers

Related papers: FlexiViT: One Model for All Patch Sizes

200 papers

Sequence models such as transformers require inputs to be represented as one-dimensional sequences. In vision, this typically involves flattening images using a fixed row-major (raster-scan) order. While full self-attention is…

Machine Learning · Computer Science 2025-10-24 Declan Kutscher , David M. Chan , Yutong Bai , Trevor Darrell , Ritwik Gupta

The absence of openly accessible data and specialized foundation models is a major barrier for computational research in surgery. Toward this, (i) we open-source the largest dataset of general surgery videos to-date, consisting of 680 hours…

Computer Vision and Pattern Recognition · Computer Science 2024-04-16 Samuel Schmidgall , Ji Woong Kim , Jeffrey Jopling , Axel Krieger

Currently, vision encoder models like Vision Transformers (ViTs) typically excel at image recognition tasks but cannot simultaneously support text recognition like human visual recognition. To address this limitation, we propose UNIT, a…

Computer Vision and Pattern Recognition · Computer Science 2024-09-09 Yi Zhu , Yanpeng Zhou , Chunwei Wang , Yang Cao , Jianhua Han , Lu Hou , Hang Xu

Transformers have recently gained significant attention in the computer vision community. However, the lack of scalability of self-attention mechanisms with respect to image size has limited their wide adoption in state-of-the-art vision…

Computer Vision and Pattern Recognition · Computer Science 2022-09-12 Zhengzhong Tu , Hossein Talebi , Han Zhang , Feng Yang , Peyman Milanfar , Alan Bovik , Yinxiao Li

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

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

Recently, Transformers have shown promising performance in various vision tasks. However, the high costs of global self-attention remain challenging for Transformers, especially for high-resolution vision tasks. Inspired by one of the most…

Computer Vision and Pattern Recognition · Computer Science 2023-11-13 Zhemin Zhang , Xun Gong

In this work we demonstrate the vulnerability of vision transformers (ViTs) to gradient-based inversion attacks. During this attack, the original data batch is reconstructed given model weights and the corresponding gradients. We introduce…

Computer Vision and Pattern Recognition · Computer Science 2022-03-29 Ali Hatamizadeh , Hongxu Yin , Holger Roth , Wenqi Li , Jan Kautz , Daguang Xu , Pavlo Molchanov

Recently, vision Transformers (ViTs) have been actively applied to fine-grained visual recognition (FGVR). ViT can effectively model the interdependencies between patch-divided object regions through an inherent self-attention mechanism. In…

Computer Vision and Pattern Recognition · Computer Science 2024-10-08 Jiyong Moon , Junseok Lee , Yunju Lee , Seongsik Park

Vision transformers (ViTs) have recently obtained success in many applications, but their intensive computation and heavy memory usage at both training and inference time limit their generalization. Previous compression algorithms usually…

Computer Vision and Pattern Recognition · Computer Science 2022-11-22 Zhenglun Kong , Haoyu Ma , Geng Yuan , Mengshu Sun , Yanyue Xie , Peiyan Dong , Xin Meng , Xuan Shen , Hao Tang , Minghai Qin , Tianlong Chen , Xiaolong Ma , Xiaohui Xie , Zhangyang Wang , Yanzhi Wang

In this paper, we propose a fully differentiable quantization method for vision transformer (ViT) named as Q-ViT, in which both of the quantization scales and bit-widths are learnable parameters. Specifically, based on our observation that…

Computer Vision and Pattern Recognition · Computer Science 2022-09-07 Zhexin Li , Tong Yang , Peisong Wang , Jian Cheng

Transformer-based models, such as BERT and ViT, have achieved state-of-the-art results across different natural language processing (NLP) and computer vision (CV) tasks. However, these models are extremely memory intensive during their…

Computation and Language · Computer Science 2023-05-31 Arash Ardakani , Altan Haan , Shangyin Tan , Doru Thom Popovici , Alvin Cheung , Costin Iancu , Koushik Sen

Vision transformers (ViTs) have gained popularity recently. Even without customized image operators such as convolutions, ViTs can yield competitive performance when properly trained on massive data. However, the computational overhead of…

Machine Learning · Computer Science 2022-03-17 Shixing Yu , Tianlong Chen , Jiayi Shen , Huan Yuan , Jianchao Tan , Sen Yang , Ji Liu , Zhangyang Wang

Vision Transformers (ViTs) can learn strong image-level representations while their patch representations become less effective for dense prediction during prolonged training. We revisit this dense degradation phenomenon and argue that it…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Linxiang Su

Vision Transformers (ViTs) have demonstrated state-of-the-art performance on many Computer Vision Tasks. Unfortunately, deploying these large-scale ViTs is resource-consuming and impossible for many mobile devices. While most in the…

Computer Vision and Pattern Recognition · Computer Science 2023-06-01 Nahid Alam , Steven Kolawole , Simardeep Sethi , Nishant Bansali , Karina Nguyen

Vision Transformers achieve impressive accuracy across a range of visual recognition tasks. Unfortunately, their accuracy frequently comes with high computational costs. This is a particular issue in video recognition, where models are…

Computer Vision and Pattern Recognition · Computer Science 2023-08-28 Matthew Dutson , Yin Li , Mohit Gupta

Neural Architecture Search (NAS) has shown promising performance in the automatic design of vision transformers (ViT) exceeding 1G FLOPs. However, designing lightweight and low-latency ViT models for diverse mobile devices remains a big…

Computer Vision and Pattern Recognition · Computer Science 2023-03-22 Chen Tang , Li Lyna Zhang , Huiqiang Jiang , Jiahang Xu , Ting Cao , Quanlu Zhang , Yuqing Yang , Zhi Wang , Mao Yang

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

This paper explores the feasibility of finding an optimal sub-model from a vision transformer and introduces a pure vision transformer slimming (ViT-Slim) framework. It can search a sub-structure from the original model end-to-end across…

Computer Vision and Pattern Recognition · Computer Science 2022-04-26 Arnav Chavan , Zhiqiang Shen , Zhuang Liu , Zechun Liu , Kwang-Ting Cheng , Eric Xing

Randomly masking and predicting word tokens has been a successful approach in pre-training language models for a variety of downstream tasks. In this work, we observe that the same idea also applies naturally to sequential decision making,…