English
Related papers

Related papers: Slicing Vision Transformer for Flexible Inference

200 papers

Vision Transformer (ViT) self-attention mechanism is characterized by feature collapse in deeper layers, resulting in the vanishing of low-level visual features. However, such features can be helpful to accurately represent and identify…

Computer Vision and Pattern Recognition · Computer Science 2024-08-06 Anxhelo Diko , Danilo Avola , Marco Cascio , Luigi Cinque

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

Humans see low spatial frequency components before high spatial frequency components. Drawing on this neuroscientific inspiration, we investigate the effect of introducing patches from different spatial frequencies into Vision Transformers…

Computer Vision and Pattern Recognition · Computer Science 2025-09-26 Yuyang Shu , Michael E. Bain

In this paper, we question if well pre-trained vision transformer (ViT) models could be used as teachers that exhibit scalable properties to advance cross architecture knowledge distillation (KD) research, in the context of using…

Computer Vision and Pattern Recognition · Computer Science 2024-11-12 Jiawei Fan , Chao Li , Xiaolong Liu , Anbang Yao

We present a neat yet effective recursive operation on vision transformers that can improve parameter utilization without involving additional parameters. This is achieved by sharing weights across the depth of transformer networks. The…

Computer Vision and Pattern Recognition · Computer Science 2022-07-27 Zhiqiang Shen , Zechun Liu , Eric Xing

We study semi-supervised learning (SSL) for vision transformers (ViT), an under-explored topic despite the wide adoption of the ViT architectures to different tasks. To tackle this problem, we propose a new SSL pipeline, consisting of first…

Computer Vision and Pattern Recognition · Computer Science 2022-08-12 Zhaowei Cai , Avinash Ravichandran , Paolo Favaro , Manchen Wang , Davide Modolo , Rahul Bhotika , Zhuowen Tu , Stefano Soatto

Recently, Vision Transformer (ViT) has achieved promising performance in image recognition and gradually serves as a powerful backbone in various vision tasks. To satisfy the sequential input of Transformer, the tail of ViT first splits…

Computer Vision and Pattern Recognition · Computer Science 2024-03-19 Yunke Wang , Bo Du , Wenyuan Wang , Chang Xu

Vision Transformers (ViTs) achieve strong data-driven scaling by leveraging all-to-all self-attention. However, this flexibility incurs a computational cost that scales quadratically with image resolution, limiting ViTs in high-resolution…

Computer Vision and Pattern Recognition · Computer Science 2026-05-13 Alan Z. Song , Yinjie Chen , Mu Nan , Rui Zhang , Jiahang Cao , Weijian Mai , Muquan Yu , Hossein Adeli , Deva Ramanan , Michael J. Tarr , Andrew F. Luo

As Vision Transformers (ViTs) are increasingly adopted in sensitive vision applications, there is a growing demand for improved interpretability. This has led to efforts to forward-align these models with carefully annotated abstract,…

Computer Vision and Pattern Recognition · Computer Science 2025-02-05 Sanchit Sinha , Guangzhi Xiong , Aidong Zhang

This paper proposes a working recipe of using Vision Transformer (ViT) in class incremental learning. Although this recipe only combines existing techniques, developing the combination is not trivial. Firstly, naive application of ViT to…

Computer Vision and Pattern Recognition · Computer Science 2022-04-19 Pei Yu , Yinpeng Chen , Ying Jin , Zicheng Liu

Vision Transformers (ViTs), with their ability to model long-range dependencies through self-attention mechanisms, have become a standard architecture in computer vision. However, the interpretability of these models remains a challenge. To…

Computer Vision and Pattern Recognition · Computer Science 2025-01-09 Walid Bousselham , Angie Boggust , Sofian Chaybouti , Hendrik Strobelt , Hilde Kuehne

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) have proven to be effective, in solving 2D image understanding tasks by training over large-scale image datasets; and meanwhile as a somehow separate track, in modeling the 3D visual world too such as voxels or…

Computer Vision and Pattern Recognition · Computer Science 2022-09-20 Yi Wang , Zhiwen Fan , Tianlong Chen , Hehe Fan , Zhangyang Wang

CRATE, a white-box transformer architecture designed to learn compressed and sparse representations, offers an intriguing alternative to standard vision transformers (ViTs) due to its inherent mathematical interpretability. Despite…

Computer Vision and Pattern Recognition · Computer Science 2025-01-15 Jinrui Yang , Xianhang Li , Druv Pai , Yuyin Zhou , Yi Ma , Yaodong Yu , Cihang Xie

Since their inception, Vision Transformers (ViTs) have emerged as a compelling alternative to Convolutional Neural Networks (CNNs) across a wide spectrum of tasks. ViTs exhibit notable characteristics, including global attention, resilience…

Computer Vision and Pattern Recognition · Computer Science 2024-07-22 Hanan Gani , Nada Saadi , Noor Hussein , Karthik Nandakumar

Vision Transformers (ViTs) dominate self-supervised learning (SSL). While they have proven highly effective for large-scale pretraining, they are computationally inefficient and scale poorly with image size. Consequently, foundational…

Computer Vision and Pattern Recognition · Computer Science 2026-04-23 Nedyalko Prisadnikov , Danda Pani Paudel , Yuqian Fu , Luc Van Gool

Vision transformers (ViTs) can be trained using various learning paradigms, from fully supervised to self-supervised. Diverse training protocols often result in significantly different feature spaces, which are usually compared through…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Johanna Vielhaben , Dilyara Bareeva , Jim Berend , Wojciech Samek , Nils Strodthoff

Vision transformers (ViTs) have gained increasing popularity as they are commonly believed to own higher modeling capacity and representation flexibility, than traditional convolutional networks. However, it is questionable whether such…

Machine Learning · Computer Science 2022-03-15 Tianlong Chen , Zhenyu Zhang , Yu Cheng , Ahmed Awadallah , Zhangyang Wang

Vision Transformers (ViTs) is emerging as an alternative to convolutional neural networks (CNNs) for visual recognition. They achieve competitive results with CNNs but the lack of the typical convolutional inductive bias makes them more…

Computer Vision and Pattern Recognition · Computer Science 2022-01-27 Yun-Hao Cao , Hao Yu , Jianxin Wu

Incorporating symmetry priors as inductive biases to design equivariant Vision Transformers (ViTs) has emerged as a promising avenue for enhancing their performance. However, existing equivariant ViTs often struggle to balance performance…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Jiahong Fu , Qi Xie , Deyu Meng , Zongben Xu