English
Related papers

Related papers: Early Convolutions Help Transformers See Better

200 papers

SGD and AdamW are the two most used optimizers for fine-tuning large neural networks in computer vision. When the two methods perform the same, SGD is preferable because it uses less memory (12 bytes/parameter with momentum and 8…

Computer Vision and Pattern Recognition · Computer Science 2023-10-11 Ananya Kumar , Ruoqi Shen , Sebastien Bubeck , Suriya Gunasekar

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

Vision Transformers (ViTs) have recently become the state-of-the-art across many computer vision tasks. In contrast to convolutional networks (CNNs), ViTs enable global information sharing even within shallow layers of a network, i.e.,…

Computer Vision and Pattern Recognition · Computer Science 2023-04-04 Jongwoo Park , Kumara Kahatapitiya , Donghyun Kim , Shivchander Sudalairaj , Quanfu Fan , Michael S. Ryoo

The transformer models have shown promising effectiveness in dealing with various vision tasks. However, compared with training Convolutional Neural Network (CNN) models, training Vision Transformer (ViT) models is more difficult and relies…

Computer Vision and Pattern Recognition · Computer Science 2022-07-28 Jiawang Bai , Li Yuan , Shu-Tao Xia , Shuicheng Yan , Zhifeng Li , Wei Liu

Recently, efficient Vision Transformers have shown great performance with low latency on resource-constrained devices. Conventionally, they use 4x4 patch embeddings and a 4-stage structure at the macro level, while utilizing sophisticated…

Computer Vision and Pattern Recognition · Computer Science 2024-03-29 Seokju Yun , Youngmin Ro

We present an approach to efficiently and effectively adapt a masked image modeling (MIM) pre-trained vanilla Vision Transformer (ViT) for object detection, which is based on our two novel observations: (i) A MIM pre-trained vanilla ViT…

Computer Vision and Pattern Recognition · Computer Science 2022-05-20 Yuxin Fang , Shusheng Yang , Shijie Wang , Yixiao Ge , Ying Shan , Xinggang Wang

This paper studies the efficiency problem for visual transformers by excavating redundant calculation in given networks. The recent transformer architecture has demonstrated its effectiveness for achieving excellent performance on a series…

Computer Vision and Pattern Recognition · Computer Science 2022-04-05 Yehui Tang , Kai Han , Yunhe Wang , Chang Xu , Jianyuan Guo , Chao Xu , Dacheng Tao

Vision transformer (ViT) is an attention neural network architecture that is shown to be effective for computer vision tasks. However, compared to ResNet-18 with a similar number of parameters, ViT has a significantly lower evaluation…

Computer Vision and Pattern Recognition · Computer Science 2023-02-09 Haoran Zhu , Boyuan Chen , Carter Yang

Recent advances in Vision Transformer (ViT) have demonstrated its impressive performance in image classification, which makes it a promising alternative to Convolutional Neural Network (CNN). Unlike CNNs, ViT represents an input image as a…

Computer Vision and Pattern Recognition · Computer Science 2022-07-19 Jindong Gu , Volker Tresp , Yao Qin

The Vision Transformer (ViT) architecture has become widely recognized in computer vision, leveraging its self-attention mechanism to achieve remarkable success across various tasks. Despite its strengths, ViT's optimization remains…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 Haoyu Yun , Hamid Krim

We attempt to reduce the computational costs in vision transformers (ViTs), which increase quadratically in the token number. We present a novel training paradigm that trains only one ViT model at a time, but is capable of providing…

Computer Vision and Pattern Recognition · Computer Science 2023-07-20 Mingbao Lin , Mengzhao Chen , Yuxin Zhang , Chunhua Shen , Rongrong Ji , Liujuan Cao

Vision transformer (ViT) has achieved competitive accuracy on a variety of computer vision applications, but its computational cost impedes the deployment on resource-limited mobile devices. We explore the sparsity in ViT and observe that…

Computer Vision and Pattern Recognition · Computer Science 2022-03-10 Zhuoran Song , Yihong Xu , Zhezhi He , Li Jiang , Naifeng Jing , Xiaoyao Liang

Vision transformer (ViT) recently has drawn great attention in computer vision due to its remarkable model capability. However, most prevailing ViT models suffer from huge number of parameters, restricting their applicability on devices…

Computer Vision and Pattern Recognition · Computer Science 2022-07-22 Kan Wu , Jinnian Zhang , Houwen Peng , Mengchen Liu , Bin Xiao , Jianlong Fu , Lu Yuan

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

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

Recently, Transformers have emerged as the go-to architecture for both vision and language modeling tasks, but their computational efficiency is limited by the length of the input sequence. To address this, several efficient variants of…

Computer Vision and Pattern Recognition · Computer Science 2023-05-18 Hao Zheng , Jinbao Wang , Xiantong Zhen , Hong Chen , Jingkuan Song , Feng Zheng

Non-overlapping patch-wise convolution is the default image tokenizer for all state-of-the-art vision Transformer (ViT) models. Even though many ViT variants have been proposed to improve its efficiency and accuracy, little research on…

Computer Vision and Pattern Recognition · Computer Science 2024-05-30 Zhenhai Zhu , Radu Soricut

Vision Transformers (ViTs) have emerged as a foundational model in computer vision, excelling in generalization and adaptation to downstream tasks. However, deploying ViTs to support diverse resource constraints typically requires…

Computer Vision and Pattern Recognition · Computer Science 2025-07-28 Chen Zhu , Wangbo Zhao , Huiwen Zhang , Samir Khaki , Yuhao Zhou , Weidong Tang , Shuo Wang , Zhihang Yuan , Yuzhang Shang , Xiaojiang Peng , Kai Wang , Dawei Yang

Vision transformers have emerged as a promising alternative to convolutional neural networks for various image analysis tasks, offering comparable or superior performance. However, one significant drawback of ViTs is their…

Computer Vision and Pattern Recognition · Computer Science 2025-04-16 Kaixin Xu , Zhe Wang , Chunyun Chen , Xue Geng , Jie Lin , Mohamed M. Sabry Aly , Xulei Yang , Min Wu , Xiaoli Li , Weisi Lin

Although transformers have become the neural architectures of choice for natural language processing, they require orders of magnitude more training data, GPU memory, and computations in order to compete with convolutional neural networks…

Computer Vision and Pattern Recognition · Computer Science 2021-10-04 Pranav Jeevan , Amit Sethi