English
Related papers

Related papers: Robustifying Token Attention for Vision Transforme…

200 papers

Transformers have elevated to the state-of-the-art vision architectures through innovations in attention mechanism inspired from visual perception. At present two classes of attentions prevail in vision transformers, regional and sparse…

Computer Vision and Pattern Recognition · Computer Science 2024-03-08 Nabil Ibtehaz , Ning Yan , Masood Mortazavi , Daisuke Kihara

Transformers, which are popular for language modeling, have been explored for solving vision tasks recently, e.g., the Vision Transformer (ViT) for image classification. The ViT model splits each image into a sequence of tokens with fixed…

Computer Vision and Pattern Recognition · Computer Science 2021-12-01 Li Yuan , Yunpeng Chen , Tao Wang , Weihao Yu , Yujun Shi , Zihang Jiang , Francis EH Tay , Jiashi Feng , Shuicheng Yan

In this paper, we propose EDIT (Encoder-Decoder Image Transformer), a novel architecture designed to mitigate the attention sink phenomenon observed in Vision Transformer models. Attention sink occurs when an excessive amount of attention…

Computer Vision and Pattern Recognition · Computer Science 2025-10-17 Wenfeng Feng , Hongxiang Wang , Jianlong Wang , Xin Zhang , Jingjing Zhao , Yueyue Liang , Xiang Chen , Duokui Han

Linear attention has emerged as a promising direction for scaling Vision Transformers beyond the quadratic cost of dense self-attention. A prevalent strategy is to compress spatial tokens into a compact set of intermediate proxies that…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Yuntong Li , Hainuo Wang , Hengxing Liu , Mingjia Li , Xiaojie Guo

Vision transformers (ViT) rely on attention mechanism to weigh input features, and therefore attention scores have naturally been considered as explanations for its decision-making process. However, attention scores are almost always…

Computer Vision and Pattern Recognition · Computer Science 2026-04-03 Neo Christopher Chung , Maxim Laletin

Transformer is a ubiquitous model for natural language processing and has attracted wide attentions in computer vision. The attention maps are indispensable for a transformer model to encode the dependencies among input tokens. However,…

Machine Learning · Computer Science 2021-02-26 Yujing Wang , Yaming Yang , Jiangang Bai , Mingliang Zhang , Jing Bai , Jing Yu , Ce Zhang , Gao Huang , Yunhai Tong

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

Standard deep learning models such as convolutional neural networks (CNNs) lack the ability of generalizing to domains which have not been seen during training. This problem is mainly due to the common but often wrong assumption of such…

Computer Vision and Pattern Recognition · Computer Science 2024-03-19 Mehrdad Noori , Milad Cheraghalikhani , Ali Bahri , Gustavo A. Vargas Hakim , David Osowiechi , Ismail Ben Ayed , Christian Desrosiers

The efficiency of large vision-language models (LVLMs) is constrained by the computational bottleneck of the attention mechanism during the prefill phase and the memory bottleneck of fetching the key-value (KV) cache in the decoding phase,…

Computer Vision and Pattern Recognition · Computer Science 2024-12-19 Yefei He , Feng Chen , Jing Liu , Wenqi Shao , Hong Zhou , Kaipeng Zhang , Bohan Zhuang

The Vision Transformer (ViT) demonstrates exceptional performance in various computer vision tasks. Attention is crucial for ViT to capture complex wide-ranging relationships among image patches, allowing the model to weigh the importance…

Machine Learning · Statistics 2024-01-22 Tomohiro Shiraishi , Daiki Miwa , Teruyuki Katsuoka , Vo Nguyen Le Duy , Kouichi Taji , Ichiro Takeuchi

The attention module is the key component in Transformers. While the global attention mechanism offers high expressiveness, its excessive computational cost restricts its applicability in various scenarios. In this paper, we propose a novel…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Dongchen Han , Tianzhu Ye , Yizeng Han , Zhuofan Xia , Siyuan Pan , Pengfei Wan , Shiji Song , Gao Huang

Transformers have recently demonstrated strong performance in computer vision, with Vision Transformers (ViTs) leveraging self-attention to capture both low-level and high-level image features. However, standard ViTs remain computationally…

Computer Vision and Pattern Recognition · Computer Science 2026-01-08 Ali El Bellaj , Mohammed-Amine Cheddadi , Rhassan Berber

We investigate the mechanism underlying a previously identified phenomenon in Vision Transformers - the emergence of high-norm tokens that lead to noisy attention maps (Darcet et al., 2024). We observe that in multiple models (e.g., CLIP,…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Nick Jiang , Amil Dravid , Alexei Efros , Yossi Gandelsman

Vision Transformers (ViTs) have demonstrated remarkable performance in various computer vision tasks. However, the high computational complexity hinders ViTs' applicability on devices with limited memory and computing resources. Although…

Computer Vision and Pattern Recognition · Computer Science 2023-10-10 Xuwei Xu , Sen Wang , Yudong Chen , Jiajun Liu

The attention mechanism has been proven effective on various visual tasks in recent years. In the semantic segmentation task, the attention mechanism is applied in various methods, including the case of both Convolution Neural Networks…

Computer Vision and Pattern Recognition · Computer Science 2024-05-10 Zheng Yuan , Jie Zhang , Yude Wang , Shiguang Shan , Xilin Chen

Recently, Vision Transformer and its variants have shown great promise on various computer vision tasks. The ability of capturing short- and long-range visual dependencies through self-attention is arguably the main source for the success.…

Computer Vision and Pattern Recognition · Computer Science 2021-07-02 Jianwei Yang , Chunyuan Li , Pengchuan Zhang , Xiyang Dai , Bin Xiao , Lu Yuan , Jianfeng Gao

Vision Transformers (ViTs) that leverage self-attention mechanism have shown superior performance on many classical vision tasks compared to convolutional neural networks (CNNs) and gain increasing popularity recently. Existing ViTs works…

Cryptography and Security · Computer Science 2024-04-29 Xinghua Xue , Cheng Liu , Ying Wang , Bing Yang , Tao Luo , Lei Zhang , Huawei Li , Xiaowei Li

Multi-head self-attention (MHSA) is a key component of Transformers, a widely popular architecture in both language and vision. Multiple heads intuitively enable different parallel processes over the same input. Yet, they also obscure the…

Computer Vision and Pattern Recognition · Computer Science 2025-07-16 Pooyan Rahmanzadehgervi , Hung Huy Nguyen , Rosanne Liu , Long Mai , Anh Totti Nguyen

The latest generation of transformer-based vision models has proven to be superior to Convolutional Neural Network (CNN)-based models across several vision tasks, largely attributed to their remarkable prowess in relation modeling.…

Computer Vision and Pattern Recognition · Computer Science 2023-12-29 Quazi Mishkatul Alam , Bilel Tarchoun , Ihsen Alouani , Nael Abu-Ghazaleh

Vision Transformer (ViT), as a powerful alternative to Convolutional Neural Network (CNN), has received much attention. Recent work showed that ViTs are also vulnerable to adversarial examples like CNNs. To build robust ViTs, an intuitive…

Computer Vision and Pattern Recognition · Computer Science 2022-07-22 Boxi Wu , Jindong Gu , Zhifeng Li , Deng Cai , Xiaofei He , Wei Liu