English
Related papers

Related papers: Auto-scaling Vision Transformers without Training

200 papers

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 Transformer (ViT) is becoming more popular in image processing. Specifically, we investigate the effectiveness of test-time adaptation (TTA) on ViT, a technique that has emerged to correct its prediction during test-time by itself.…

Computer Vision and Pattern Recognition · Computer Science 2022-06-29 Takeshi Kojima , Yutaka Matsuo , Yusuke Iwasawa

The recent breakthroughs in natural language processing for model pretraining on large quantities of data have opened the way for similar foundation models in computer vision. These models could greatly simplify the use of images in any…

Transformers are remarkably versatile, suggesting the existence of generic inductive biases beneficial across modalities. In this work, we explore a new way to instil such biases in vision transformers (ViTs) through pretraining on…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Zachary Shinnick , Liangze Jiang , Hemanth Saratchandran , Damien Teney , Anton van den Hengel

Data-free quantization can potentially address data privacy and security concerns in model compression, and thus has been widely investigated. Recently, PSAQ-ViT designs a relative value metric, patch similarity, to generate data from…

Computer Vision and Pattern Recognition · Computer Science 2023-08-01 Zhikai Li , Mengjuan Chen , Junrui Xiao , Qingyi Gu

Transformers have achieved remarkable success across a wide range of applications, a feat often attributed to their scalability. Yet training them without skip (residual) connections remains notoriously difficult. While skips stabilize…

Machine Learning · Computer Science 2025-10-02 Yiping Ji , James Martens , Jianqiao Zheng , Ziqin Zhou , Peyman Moghadam , Xinyu Zhang , Hemanth Saratchandran , Simon Lucey

Vision Transformers (ViTs) achieve state-of-the-art performance on challenging vision tasks, but their deployment on edge devices is severely hindered by the computational complexity and global reduction bottleneck imposed by layer…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Kieran Carrigg , Sigur de Vries , Amirhossein Sadough , Marcel van Gerven

Large pretrained plain vision Transformers (ViTs) have been the workhorse for many downstream tasks. However, existing works utilizing off-the-shelf ViTs are inefficient in terms of training and deployment, because adopting ViTs with…

Computer Vision and Pattern Recognition · Computer Science 2023-11-29 Zizheng Pan , Jing Liu , Haoyu He , Jianfei Cai , Bohan Zhuang

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

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

Deeper Vision Transformers (ViTs) are more challenging to train. We expose a degradation problem in deeper layers of ViT when using masked image modeling (MIM) for pre-training. To ease the training of deeper ViTs, we introduce a…

Computer Vision and Pattern Recognition · Computer Science 2023-11-16 Guoxi Huang , Hongtao Fu , Adrian G. Bors

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

We address the task of weakly-supervised few-shot image classification and segmentation, by leveraging a Vision Transformer (ViT) pretrained with self-supervision. Our proposed method takes token representations from the self-supervised ViT…

Computer Vision and Pattern Recognition · Computer Science 2023-07-10 Dahyun Kang , Piotr Koniusz , Minsu Cho , Naila Murray

Vision Transformers (ViTs) represent a groundbreaking shift in machine learning approaches to computer vision. Unlike traditional approaches, ViTs employ the self-attention mechanism, which has been widely used in natural language…

Computer Vision and Pattern Recognition · Computer Science 2025-06-12 Mohammad Erfan Sadeghi , Arash Fayyazi , Suhas Somashekar , Armin Abdollahi , Massoud Pedram

Data-Free Quantization (DFQ) enables the quantization of Vision Transformers (ViTs) without requiring access to data, allowing for the deployment of ViTs on devices with limited resources. In DFQ, the quantization model must be calibrated…

Computer Vision and Pattern Recognition · Computer Science 2025-07-22 Yujia Tong , Jingling Yuan , Tian Zhang , Jianquan Liu , Chuang Hu

Prior works have proposed several strategies to reduce the computational cost of self-attention mechanism. Many of these works consider decomposing the self-attention procedure into regional and local feature extraction procedures that each…

Computer Vision and Pattern Recognition · Computer Science 2022-07-13 Ting Yao , Yehao Li , Yingwei Pan , Yu Wang , Xiao-Ping Zhang , Tao Mei

For state-of-the-art image understanding, Vision Transformers (ViTs) have become the standard architecture but their processing diverges substantially from human attentional characteristics. We investigate whether this cognitive gap can be…

Computer Vision and Pattern Recognition · Computer Science 2026-04-23 Ethan Knights

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

Self-Supervised Learning (SSL) for Vision Transformers (ViTs) has recently demonstrated considerable potential as a pre-training strategy for a variety of computer vision tasks, including image classification and segmentation, both in…

Computer Vision and Pattern Recognition · Computer Science 2025-09-22 Yannis Kaltampanidis , Alexandros Doumanoglou , Dimitrios Zarpalas

This paper presents a new Vision Transformer (ViT) architecture Multi-Scale Vision Longformer, which significantly enhances the ViT of \cite{dosovitskiy2020image} for encoding high-resolution images using two techniques. The first is the…

Computer Vision and Pattern Recognition · Computer Science 2021-05-28 Pengchuan Zhang , Xiyang Dai , Jianwei Yang , Bin Xiao , Lu Yuan , Lei Zhang , Jianfeng Gao