English
Related papers

Related papers: What do Vision Transformers Learn? A Visual Explor…

200 papers

Why are state-of-the-art Vision Transformers (ViTs) not designed to exploit natural geometric symmetries such as 90-degree rotations and reflections? In this paper, we argue that there is no fundamental reason, and what has been missing is…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 David Nordström , Johan Edstedt , Fredrik Kahl , Georg Bökman

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 Transformers (ViTs) have shown remarkable performance and scalability across various computer vision tasks. To apply single-scale ViTs to image segmentation, existing methods adopt a convolutional adapter to generate multi-scale…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Tommie Kerssies , Niccolò Cavagnero , Alexander Hermans , Narges Norouzi , Giuseppe Averta , Bastian Leibe , Gijs Dubbelman , Daan de Geus

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

The success of multi-head self-attentions (MSAs) for computer vision is now indisputable. However, little is known about how MSAs work. We present fundamental explanations to help better understand the nature of MSAs. In particular, we…

Computer Vision and Pattern Recognition · Computer Science 2022-06-09 Namuk Park , Songkuk Kim

Vision Transformers (ViTs) have demonstrated state-of-the-art performance on many Computer Vision Tasks. Unfortunately, deploying these large-scale ViTs is resource-consuming and impossible for many mobile devices. While most in the…

Computer Vision and Pattern Recognition · Computer Science 2023-06-01 Nahid Alam , Steven Kolawole , Simardeep Sethi , Nishant Bansali , Karina Nguyen

Vision Transformers (ViTs) can learn strong image-level representations while their patch representations become less effective for dense prediction during prolonged training. We revisit this dense degradation phenomenon and argue that it…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Linxiang Su

Since being introduced in 2020, Vision Transformers (ViT) has been steadily breaking the record for many vision tasks and are often described as ``all-you-need" to replace ConvNet. Despite that, ViTs are generally computational,…

Computer Vision and Pattern Recognition · Computer Science 2022-07-11 Chuong H. Nguyen , Su Huynh , Vinh Nguyen , Ngoc Nguyen

Given the significant advances in machine learning techniques on mobile devices, particularly in the domain of computer vision, in this work we quantitatively study the performance characteristics of 190 real-world vision transformers…

Computer Vision and Pattern Recognition · Computer Science 2026-02-20 Zhuojin Li , Marco Paolieri , Leana Golubchik

Extensive work has demonstrated the effectiveness of Vision Transformers. The plain Vision Transformer tends to obtain multi-scale features by selecting fixed layers, or the last layer of features aiming to achieve higher performance in…

Computer Vision and Pattern Recognition · Computer Science 2023-05-10 Fangjian Lin , Yizhe Ma , Shengwei Tian

Shortcut learning, where machine learning models exploit spurious correlations in data instead of capturing meaningful features, poses a significant challenge to building robust and generalizable models. This phenomenon is prevalent across…

Machine Learning · Computer Science 2025-09-03 Pirzada Suhail , Vrinda Goel , Amit Sethi

We apply pre-trained Vision Transformers (ViTs), originally developed for image recognition, to the analysis of astronomical spectral data. By converting traditional one-dimensional spectra into two-dimensional image representations, we…

Instrumentation and Methods for Astrophysics · Physics 2026-05-13 Luis Felipe Strano Moraes , Ignacio Becker , Pavlos Protopapas , Guillermo Cabrera-Vives

Vision Transformers (ViTs) have revolutionized computer vision by leveraging self-attention to model long-range dependencies. However, ViTs face challenges such as high computational costs due to the quadratic scaling of self-attention and…

Computer Vision and Pattern Recognition · Computer Science 2025-04-22 Zhoujie Qian

Learning efficient and expressive visual representation has long been the pursuit of computer vision research. While Vision Transformers (ViTs) gradually replace traditional Convolutional Neural Networks (CNNs) as more scalable vision…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Quan Kong , Yanru Xiao , Yuhao Shen , Cong Wang

Vision Transformers (ViTs) have delivered remarkable progress through global self-attention, yet their quadratic complexity can become prohibitive for high-resolution inputs. In this work, we present ViT-Linearizer, a cross-architecture…

Computer Vision and Pattern Recognition · Computer Science 2026-02-27 Guoyizhe Wei , Rama Chellappa

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) have gained popularity recently. Even without customized image operators such as convolutions, ViTs can yield competitive performance when properly trained on massive data. However, the computational overhead of…

Machine Learning · Computer Science 2022-03-17 Shixing Yu , Tianlong Chen , Jiayi Shen , Huan Yuan , Jianchao Tan , Sen Yang , Ji Liu , Zhangyang Wang

Vision Transformers (ViTs) and Swin Transformers (Swin) are currently state-of-the-art in computational pathology. However, domain experts are still reluctant to use these models due to their lack of interpretability. This is not…

Computer Vision and Pattern Recognition · Computer Science 2024-01-19 Manuel Tran , Amal Lahiani , Yashin Dicente Cid , Melanie Boxberg , Peter Lienemann , Christian Matek , Sophia J. Wagner , Fabian J. Theis , Eldad Klaiman , Tingying Peng

Vision Transformers (ViTs) have shown promising performance compared with Convolutional Neural Networks (CNNs), but the training of ViTs is much harder than CNNs. In this paper, we define several metrics, including Dynamic Data Proportion…

Computer Vision and Pattern Recognition · Computer Science 2022-09-30 Benjia Zhou , Pichao Wang , Jun Wan , Yanyan Liang , Fan Wang

In the last decade, convolutional neural networks (ConvNets) have dominated and achieved state-of-the-art performances in a variety of medical imaging applications. However, the performances of ConvNets are still limited by lacking the…

Image and Video Processing · Electrical Eng. & Systems 2021-04-15 Junyu Chen , Yufan He , Eric C. Frey , Ye Li , Yong Du