English
Related papers

Related papers: Robustifying Token Attention for Vision Transforme…

200 papers

Convolutional networks and vision transformers have different forms of pairwise interactions, pooling across layers and pooling at the end of the network. Does the latter really need to be different? As a by-product of pooling, vision…

Computer Vision and Pattern Recognition · Computer Science 2023-09-14 Bill Psomas , Ioannis Kakogeorgiou , Konstantinos Karantzalos , Yannis Avrithis

Vision Transformers (ViTs) have demonstrated strong performance across a range of computer vision tasks by modeling long-range spatial interactions via self-attention. However, channel-wise mixing in ViTs remains static, relying on fixed…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Aon Safdar , Mohamed Saadeldin

Vision transformers (ViTs) have achieved promising results on a variety of Computer Vision tasks, however their quadratic complexity in the number of input tokens has limited their application specially in resource-constrained settings.…

Computer Vision and Pattern Recognition · Computer Science 2024-01-09 Wentao Zhu

Modern vision transformers leverage visually inspired local interaction between pixels through attention computed within window or grid regions, in contrast to the global attention employed in the original ViT. Regional attention restricts…

Computer Vision and Pattern Recognition · Computer Science 2024-06-14 Nabil Ibtehaz , Ning Yan , Masood Mortazavi , Daisuke Kihara

Transformer-based methods have demonstrated strong potential in hyperspectral pansharpening by modeling long-range dependencies. However, their effectiveness is often limited by redundant token representations and a lack of multi-scale…

Computer Vision and Pattern Recognition · Computer Science 2025-08-12 Hongkun Jin , Hongcheng Jiang , Zejun Zhang , Yuan Zhang , Jia Fu , Tingfeng Li , Kai Luo

Vision-language models (VLMs) typically encode substantially more visual tokens than text tokens, resulting in significant token redundancy. Pruning uninformative visual tokens is therefore crucial for improving computational efficiency,…

Computer Vision and Pattern Recognition · Computer Science 2026-01-19 Kai Zhao , Wubang Yuan , Yuchen Lin , Liting Ruan , Xiaofeng Lu , Deng-Ping Fan , Ming-Ming Cheng , Dan Zeng

Vision Transformers (ViTs) face severe computational bottlenecks due to the quadratic complexity of self-attention at high resolutions. Existing token reduction methods rely on local metrics - such as single-layer attention scores - that…

Machine Learning · Computer Science 2026-05-22 Jaehyuk Lee , Hanyoung Kim , Yanggee Kim , Donghun Lee

This work aims to improve the efficiency of vision transformers (ViT). While ViTs use computationally expensive self-attention operations in every layer, we identify that these operations are highly correlated across layers -- a key…

Computer Vision and Pattern Recognition · Computer Science 2023-01-18 Shashanka Venkataramanan , Amir Ghodrati , Yuki M. Asano , Fatih Porikli , Amirhossein Habibian

Following the success in advancing natural language processing and understanding, transformers are expected to bring revolutionary changes to computer vision. This work provides a comprehensive study on the robustness of vision transformers…

Computer Vision and Pattern Recognition · Computer Science 2022-11-04 Rulin Shao , Zhouxing Shi , Jinfeng Yi , Pin-Yu Chen , Cho-Jui Hsieh

Vision transformer (ViT) expands the success of transformer models from sequential data to images. The model decomposes an image into many smaller patches and arranges them into a sequence. Multi-head self-attentions are then applied to the…

Machine Learning · Computer Science 2023-03-27 Yiran Li , Junpeng Wang , Xin Dai , Liang Wang , Chin-Chia Michael Yeh , Yan Zheng , Wei Zhang , Kwan-Liu Ma

The quadratic complexity of attention remains the central bottleneck in long-context inference for large language models. Prior acceleration methods either sparsify the attention map with structured patterns or permanently evict tokens at…

Computation and Language · Computer Science 2026-05-04 Dongwon Jo , Beomseok Kang , Jiwon Song , Jae-Joon Kim

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) with self-attention modules have recently achieved great empirical success in many vision tasks. Due to non-convex interactions across layers, however, theoretical learning and generalization analysis is mostly…

Machine Learning · Computer Science 2023-11-15 Hongkang Li , Meng Wang , Sijia Liu , Pin-yu Chen

Vision Transformer (ViT) has emerged as a prominent backbone for computer vision. For more efficient ViTs, recent works lessen the quadratic cost of the self-attention layer by pruning or fusing the redundant tokens. However, these works…

Computer Vision and Pattern Recognition · Computer Science 2024-04-02 Sanghyeok Lee , Joonmyung Choi , Hyunwoo J. Kim

Token compression techniques have recently emerged as powerful tools for accelerating Vision Transformer (ViT) inference in computer vision. Due to the quadratic computational complexity with respect to the token sequence length, these…

Computer Vision and Pattern Recognition · Computer Science 2025-07-15 Phat Nguyen , Ngai-Man Cheung

Over the past few years, vision transformers (ViTs) have consistently demonstrated remarkable performance across various visual recognition tasks. However, attempts to enhance their robustness have yielded limited success, mainly focusing…

Computer Vision and Pattern Recognition · Computer Science 2024-10-01 Nick Nikzad , Yi Liao , Yongsheng Gao , Jun Zhou

The evolution of Vision Transformers has led to their widespread adaptation to different domains. Despite large-scale success, there remain significant challenges including their reliance on extensive computational and memory resources for…

Computer Vision and Pattern Recognition · Computer Science 2025-06-24 Suyash Gaurav , Muhammad Farhan Humayun , Jukka Heikkonen , Jatin Chaudhary

Conventional wisdom suggests that pre-training Vision Transformers (ViT) improves downstream performance by learning useful representations. Is this actually true? We investigate this question and find that the features and representations…

Machine Learning · Computer Science 2024-11-15 Alexander C. Li , Yuandong Tian , Beidi Chen , Deepak Pathak , Xinlei Chen

Vision Transformers (ViTs) have demonstrated superior performance across a wide range of computer vision tasks. However, structured noise artifacts in their feature maps hinder downstream applications such as segmentation and depth…

Computer Vision and Pattern Recognition · Computer Science 2025-09-25 Sumit Mamtani

Vision transformers rely on a patch token based self attention mechanism, in contrast to convolutional networks. We investigate fundamental differences between these two families of models, by designing a block sparsity based adversarial…

Computer Vision and Pattern Recognition · Computer Science 2021-10-12 Ameya Joshi , Gauri Jagatap , Chinmay Hegde