English
Related papers

Related papers: Vision Transformers Need More Than Registers

200 papers

Despite the popularity of Vision Transformers (ViTs) and eXplainable AI (XAI), only a few explanation methods have been designed specially for ViTs thus far. They mostly use attention weights of the [CLS] token on patch embeddings and often…

Computer Vision and Pattern Recognition · Computer Science 2023-06-12 Weiyan Xie , Xiao-Hui Li , Caleb Chen Cao , Nevin L. Zhang

Vision Transformers (ViTs) take all the image patches as tokens and construct multi-head self-attention (MHSA) among them. Complete leverage of these image tokens brings redundant computations since not all the tokens are attentive in MHSA.…

Computer Vision and Pattern Recognition · Computer Science 2022-04-15 Youwei Liang , Chongjian Ge , Zhan Tong , Yibing Song , Jue Wang , Pengtao Xie

Transformers have emerged as a competitive alternative to convnets in vision tasks, yet they lack the architectural inductive bias of convnets, which may hinder their potential performance. Specifically, Vision Transformers (ViTs) are not…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Hagay Michaeli , Daniel Soudry

The quadratic computational complexity to the number of tokens limits the practical applications of Vision Transformers (ViTs). Several works propose to prune redundant tokens to achieve efficient ViTs. However, these methods generally…

Computer Vision and Pattern Recognition · Computer Science 2023-03-31 Shuning Chang , Pichao Wang , Ming Lin , Fan Wang , David Junhao Zhang , Rong Jin , Mike Zheng Shou

Vision Transformers, ViTs, have emerged as a powerful alternative to convolutional neural networks, CNNs, in a variety of image-based tasks. While CNNs have previously been evaluated for their ability to perform graphical perception tasks,…

Computer Vision and Pattern Recognition · Computer Science 2026-02-23 Poonam Poonam , Pere-Pau Vázquez , Timo Ropinski

Transformer design is the de facto standard for natural language processing tasks. The success of the transformer design in natural language processing has lately piqued the interest of researchers in the domain of computer vision. When…

Computer Vision and Pattern Recognition · Computer Science 2024-02-29 Md Sohag Mia , Abu Bakor Hayat Arnob , Abdu Naim , Abdullah Al Bary Voban , Md Shariful Islam

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

The extension of convolutional neural networks (CNNs) to non-Euclidean geometries has led to multiple frameworks for studying manifolds. Many of those methods have shown design limitations resulting in poor modelling of long-range…

Computer Vision and Pattern Recognition · Computer Science 2022-06-01 Simon Dahan , Logan Z. J. Williams , Abdulah Fawaz , Daniel Rueckert , Emma C. Robinson

We study a crucial yet often overlooked issue inherent to Vision Transformers (ViTs): feature maps of these models exhibit grid-like artifacts, which hurt the performance of ViTs in downstream dense prediction tasks such as semantic…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Jiawei Yang , Katie Z Luo , Jiefeng Li , Congyue Deng , Leonidas Guibas , Dilip Krishnan , Kilian Q Weinberger , Yonglong Tian , Yue Wang

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

Vision Transformers (ViTs) are normally regarded as a stack of transformer layers. In this work, we propose a novel view of ViTs showing that they can be seen as ensemble networks containing multiple parallel paths with different lengths.…

Computer Vision and Pattern Recognition · Computer Science 2023-08-15 Shuning Chang , Pichao Wang , Hao Luo , Fan Wang , Mike Zheng Shou

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

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…

Vision Transformer (ViT) is emerging as the state-of-the-art architecture for image recognition. While recent studies suggest that ViTs are more robust than their convolutional counterparts, our experiments find that ViTs trained on…

Computer Vision and Pattern Recognition · Computer Science 2022-04-05 Chengzhi Mao , Lu Jiang , Mostafa Dehghani , Carl Vondrick , Rahul Sukthankar , Irfan Essa

The Vision Transformer (ViT) leverages the Transformer's encoder to capture global information by dividing images into patches and achieves superior performance across various computer vision tasks. However, the self-attention mechanism of…

Computer Vision and Pattern Recognition · Computer Science 2025-01-17 Tianxiao Zhang , Wenju Xu , Bo Luo , Guanghui Wang

Vision Transformers (ViTs) have recently become the state-of-the-art across many computer vision tasks. In contrast to convolutional networks (CNNs), ViTs enable global information sharing even within shallow layers of a network, i.e.,…

Computer Vision and Pattern Recognition · Computer Science 2023-04-04 Jongwoo Park , Kumara Kahatapitiya , Donghyun Kim , Shivchander Sudalairaj , Quanfu Fan , Michael S. Ryoo

Intrigued by the inherent ability of the human visual system to identify salient regions in complex scenes, attention mechanisms have been seamlessly integrated into various Computer Vision (CV) tasks. Building upon this paradigm, Vision…

Recently, the Vision Transformer (ViT), which applied the transformer structure to the image classification task, has outperformed convolutional neural networks. However, the high performance of the ViT results from pre-training using a…

Computer Vision and Pattern Recognition · Computer Science 2021-12-28 Seung Hoon Lee , Seunghyun Lee , Byung Cheol Song

Vision Transformers (ViTs) partition input images into uniformly sized patches regardless of their content, resulting in long input sequence lengths for high-resolution images. We present Adaptive Patch Transformers (APT), which addresses…

Computer Vision and Pattern Recognition · Computer Science 2026-04-24 Rohan Choudhury , JungEun Kim , Jinhyung Park , Eunho Yang , László A. Jeni , Kris M. Kitani

Vision transformers (ViTs) have been successfully applied in image classification tasks recently. In this paper, we show that, unlike convolution neural networks (CNNs)that can be improved by stacking more convolutional layers, the…

Computer Vision and Pattern Recognition · Computer Science 2021-04-20 Daquan Zhou , Bingyi Kang , Xiaojie Jin , Linjie Yang , Xiaochen Lian , Zihang Jiang , Qibin Hou , Jiashi Feng