English
Related papers

Related papers: Leveraging Registers in Vision Transformers for Ro…

200 papers

Vision Transformers (ViTs) have emerged as the dominant architecture for visual processing tasks, demonstrating excellent scalability with increased training data and model size. However, recent work has identified the emergence of artifact…

Computer Vision and Pattern Recognition · Computer Science 2025-11-19 Yinjie Chen , Zipeng Yan , Chong Zhou , Bo Dai , Andrew F. Luo

Vision Transformers (ViTs) are known to exhibit high-norm patch-token outliers that degrade feature map quality, a problem effectively mitigated by \textit{register tokens}. As diffusion models increasingly adopt transformer architectures…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Nikita Starodubcev , Ilia Sudakov , Ilya Drobyshevskiy , Artem Babenko , Dmitry Baranchuk

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

Transformers have recently emerged as a powerful tool for learning visual representations. In this paper, we identify and characterize artifacts in feature maps of both supervised and self-supervised ViT networks. The artifacts correspond…

Computer Vision and Pattern Recognition · Computer Science 2024-04-15 Timothée Darcet , Maxime Oquab , Julien Mairal , Piotr Bojanowski

Drawing inspiration from recent findings including surprisingly decent performance of transformers without positional encoding (NoPE) in the domain of language models and how registers (additional throwaway tokens not tied to input) may…

Computation and Language · Computer Science 2026-01-23 Jason Chuan-Chih Chou , Abhinav Kumar , Shivank Garg

Training Vision Transformers (ViTs) presents significant challenges, one of which is the emergence of artifacts in attention maps, hindering their interpretability. Darcet et al. (2024) investigated this phenomenon and attributed it to the…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Spiros Baxevanakis , Platon Karageorgis , Ioannis Dravilas , Konrad Szewczyk

Vision Transformers (ViTs), when pre-trained on large-scale data, provide general-purpose representations for diverse downstream tasks. However, artifacts in ViTs are widely observed across different supervision paradigms and downstream…

Computer Vision and Pattern Recognition · Computer Science 2026-04-15 Cheng Shi , Yizhou Yu , Sibei Yang

Recent work has shown that the attention maps of the widely popular DINOv2 model exhibit artifacts, which hurt both model interpretability and performance on dense image tasks. These artifacts emerge due to the model repurposing patch…

Computer Vision and Pattern Recognition · Computer Science 2025-10-27 Alexander Lappe , Martin A. Giese

Vision Transformers (ViTs) have successfully been applied to image classification problems where large annotated datasets are available. On the other hand, when fewer annotations are available, such as in biomedical applications, image…

Computer Vision and Pattern Recognition · Computer Science 2023-06-21 Felipe A. Quezada , Carlos F. Navarro , Cristian Muñoz , Manuel Zamorano , Jorge Jara-Wilde , Violeta Chang , Cristóbal A. Navarro , Mauricio Cerda

Recent advancements in vision-language models (VLMs) have expanded their potential for real-world applications, enabling these models to perform complex reasoning on images. In the widely used fully autoregressive transformer-based models…

Computer Vision and Pattern Recognition · Computer Science 2024-10-21 Yuxin Wen , Qingqing Cao , Qichen Fu , Sachin Mehta , Mahyar Najibi

Vision Transformer (ViT) architectures represent images as collections of high-dimensional vectorized tokens, each corresponding to a rectangular non-overlapping patch. This representation trades spatial granularity for embedding…

Computer Vision and Pattern Recognition · Computer Science 2024-05-08 Dong Lao , Yangchao Wu , Tian Yu Liu , Alex Wong , Stefano Soatto

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

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 a variety of vision tasks. Despite their promising capabilities, training a ViT requires a large amount of diverse data. Several studies empirically found that using…

Computer Vision and Pattern Recognition · Computer Science 2024-05-24 Bum Jun Kim , Sang Woo Kim

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

We study outlier tokens in Diffusion Transformers (DiTs) for image generation. Prior work has shown that Vision Transformers (ViTs) can produce a small number of high-norm tokens that attract disproportionate attention while carrying…

Computer Vision and Pattern Recognition · Computer Science 2026-05-07 Xiaoyu Wu , Yifei Wang , Tsu-Jui Fu , Liang-Chieh Chen , Zhe Gan , Chen Wei

In this paper, we present token labeling -- a new training objective for training high-performance vision transformers (ViTs). Different from the standard training objective of ViTs that computes the classification loss on an additional…

Computer Vision and Pattern Recognition · Computer Science 2021-06-10 Zihang Jiang , Qibin Hou , Li Yuan , Daquan Zhou , Yujun Shi , Xiaojie Jin , Anran Wang , Jiashi Feng

Vision transformers (ViTs) achieve remarkable performance on large datasets, but tend to perform worse than convolutional neural networks (CNNs) when trained from scratch on smaller datasets, possibly due to a lack of local inductive bias…

Computer Vision and Pattern Recognition · Computer Science 2023-05-16 Ibrahim Batuhan Akkaya , Senthilkumar S. Kathiresan , Elahe Arani , Bahram Zonooz

Vision Transformers (ViTs) have recently dominated a range of computer vision tasks, yet it suffers from low training data efficiency and inferior local semantic representation capability without appropriate inductive bias. Convolutional…

Computer Vision and Pattern Recognition · Computer Science 2022-08-02 Cong Wang , Hongmin Xu , Xiong Zhang , Li Wang , Zhitong Zheng , Haifeng Liu

Vision Transformer (ViT) and its variants (e.g., Swin, PVT) have achieved great success in various computer vision tasks, owing to their capability to learn long-range contextual information. Layer Normalization (LN) is an essential…

Computer Vision and Pattern Recognition · Computer Science 2022-10-17 Wenqi Shao , Yixiao Ge , Zhaoyang Zhang , Xuyuan Xu , Xiaogang Wang , Ying Shan , Ping Luo
‹ Prev 1 2 3 10 Next ›