English
Related papers

Related papers: Cutting the Skip: Training Residual-Free Transform…

200 papers

Prompt learning is an efficient approach to adapt transformers by inserting learnable set of parameters into the input and intermediate representations of a pre-trained model. In this work, we present Expressive Prompts with Residuals…

Computer Vision and Pattern Recognition · Computer Science 2023-03-29 Rajshekhar Das , Yonatan Dukler , Avinash Ravichandran , Ashwin Swaminathan

Vision Transformers (ViTs) have become ubiquitous in computer vision. Despite their success, ViTs lack inductive biases, which can make it difficult to train them with limited data. To address this challenge, prior studies suggest training…

Computer Vision and Pattern Recognition · Computer Science 2023-12-29 Srijan Das , Tanmay Jain , Dominick Reilly , Pranav Balaji , Soumyajit Karmakar , Shyam Marjit , Xiang Li , Abhijit Das , Michael S. Ryoo

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) have demonstrated remarkable potential in image processing tasks by utilizing self-attention mechanisms to capture global relationships within data. However, their scalability is hindered by significant…

Machine Learning · Computer Science 2026-02-25 Huy Trinh , Rebecca Ma , Zeqi Yu , Tahsin Reza

How do vision transformers (ViTs) represent and process the world? This paper addresses this long-standing question through the first systematic analysis of 6.6K features across all layers, extracted via sparse autoencoders, and by…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Jinyeong Kim , Junhyeok Kim , Yumin Shim , Joohyeok Kim , Sunyoung Jung , Seong Jae Hwang

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

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

Large-scale transformer training and deployment are increasingly constrained by the transfer of activations, gradients, and optimizer states across accelerators. Low-bit quantization offers a natural remedy, but transformer activations are…

Machine Learning · Computer Science 2026-05-26 Yiping Ji , Mahalakshmi Sabanayagam , Peyman Moghadam , Hemanth Saratchandran , Simon Lucey

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

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

In this paper, we investigate the continual learning of Vision Transformers (ViT) for the challenging exemplar-free scenario, with special focus on how to efficiently distill the knowledge of its crucial self-attention mechanism (SAM). Our…

Computer Vision and Pattern Recognition · Computer Science 2022-05-06 Francesco Pelosin , Saurav Jha , Andrea Torsello , Bogdan Raducanu , Joost van de Weijer

Loss of plasticity refers to the progressive inability of a model to adapt to new tasks and poses a fundamental challenge for continual learning. While this phenomenon has been extensively studied in homogeneous neural architectures, such…

Machine Learning · Computer Science 2026-03-10 Caihao Sun , Mingqi Yuan , Shiyuan Wang , Jiayu Chen

Self-supervised learning methods are gaining increasing traction in computer vision due to their recent success in reducing the gap with supervised learning. In natural language processing (NLP) self-supervised learning and transformers are…

Computer Vision and Pattern Recognition · Computer Science 2022-12-29 Sara Atito , Muhammad Awais , Josef Kittler

Vision transformers (ViTs) are top performing models on many computer vision benchmarks and can accurately predict human behavior on object recognition tasks. However, researchers question the value of using ViTs as models of biological…

Computer Vision and Pattern Recognition · Computer Science 2023-12-06 Lalit Pandey , Samantha M. W. Wood , Justin N. Wood

Vision transformers (ViTs) have become the popular structures and outperformed convolutional neural networks (CNNs) on various vision tasks. However, such powerful transformers bring a huge computation burden, because of the exhausting…

Computer Vision and Pattern Recognition · Computer Science 2022-09-13 Zhuofan Zong , Kunchang Li , Guanglu Song , Yali Wang , Yu Qiao , Biao Leng , Yu Liu

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) are built by stacking independently parameterized blocks, but it remains unclear how much of this depth requires layer specific transformations and how much can be realized through recurrent computation. We study…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Michal Byra , Pawel Olszowiec , Grzegorz Stefanski , Grzegorz Gruszczynski , Alberto Presta

Vision Transformers (ViTs) is emerging as an alternative to convolutional neural networks (CNNs) for visual recognition. They achieve competitive results with CNNs but the lack of the typical convolutional inductive bias makes them more…

Computer Vision and Pattern Recognition · Computer Science 2022-01-27 Yun-Hao Cao , Hao Yu , Jianxin Wu

In order to autonomously learn wide repertoires of complex skills, robots must be able to learn from their own autonomously collected data, without human supervision. One learning signal that is always available for autonomously collected…

Robotics · Computer Science 2017-10-18 Frederik Ebert , Chelsea Finn , Alex X. Lee , Sergey Levine

Deriving tight Lipschitz bounds for transformer-based architectures presents a significant challenge. The large input sizes and high-dimensional attention modules typically prove to be crucial bottlenecks during the training process and…

Machine Learning · Computer Science 2025-03-20 Rohan Menon , Nicola Franco , Stephan Günnemann