English
Related papers

Related papers: A Closer Look at Self-Supervised Lightweight Visio…

200 papers

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 have spurred incredible progress in self-supervised pretraining for vision. We investigate what factors may play a role in the utility of these pretraining methods for practitioners. To do this, we evaluate various…

Computer Vision and Pattern Recognition · Computer Science 2020-04-01 Alejandro Newell , Jia Deng

The large pre-trained vision transformers (ViTs) have demonstrated remarkable performance on various visual tasks, but suffer from expensive computational and memory cost problems when deployed on resource-constrained devices. Among the…

Computer Vision and Pattern Recognition · Computer Science 2022-10-14 Yanjing Li , Sheng Xu , Baochang Zhang , Xianbin Cao , Peng Gao , Guodong Guo

Recently, plain vision Transformers (ViTs) have shown impressive performance on various computer vision tasks, thanks to their strong modeling capacity and large-scale pretraining. However, they have not yet conquered the problem of image…

Computer Vision and Pattern Recognition · Computer Science 2023-06-01 Jingfeng Yao , Xinggang Wang , Shusheng Yang , Baoyuan Wang

The Masked autoencoder (MAE) has drawn attention as a representative self-supervised approach for masked image modeling with vision transformers. However, even though MAE shows better generalization capability than fully supervised training…

Computer Vision and Pattern Recognition · Computer Science 2024-05-29 Youngwan Lee , Jeffrey Ryan Willette , Jonghee Kim , Sung Ju Hwang

Vision Transformers (ViTs) outperforms convolutional neural networks (CNNs) in several vision tasks with its global modeling capabilities. However, ViT lacks the inductive bias inherent to convolution making it require a large amount of…

Computer Vision and Pattern Recognition · Computer Science 2023-01-11 Jiawei Mao , Honggu Zhou , Xuesong Yin , Yuanqi Chang. Binling Nie. Rui Xu

Vision Transformers (ViT) have recently demonstrated the significant potential of transformer architectures for computer vision. To what extent can image-based deep reinforcement learning also benefit from ViT architectures, as compared to…

Machine Learning · Computer Science 2022-05-17 Tianxin Tao , Daniele Reda , Michiel van de Panne

This paper does not introduce a novel method per se. Instead, we address the neglected potential of hard negative samples in self-supervised learning. Previous works explored synthetic hard negatives but rarely in the context of vision…

Computer Vision and Pattern Recognition · Computer Science 2025-09-03 Nikolaos Giakoumoglou , Andreas Floros , Kleanthis Marios Papadopoulos , Tania Stathaki

Transformer-based architectures have become a dominant paradigm in vision and language, but their success is often attributed to large model capacity and massive training data. In this work, we examine how self-supervised pre-training,…

Computer Vision and Pattern Recognition · Computer Science 2026-01-06 Oli Bridge , Huey Sun , Botond Branyicskai-Nagy , Charles D'Ornano , Shomit Basu

Pre-training a large transformer model on a massive amount of unlabeled data and fine-tuning it on labeled datasets for diverse downstream tasks has proven to be a successful strategy, for a variety of vision and natural language processing…

Computer Vision and Pattern Recognition · Computer Science 2023-06-12 Seanie Lee , Minki Kang , Juho Lee , Sung Ju Hwang , Kenji Kawaguchi

Multi-scale Vision Transformer (ViT) has emerged as a powerful backbone for computer vision tasks, while the self-attention computation in Transformer scales quadratically w.r.t. the input patch number. Thus, existing solutions commonly…

Computer Vision and Pattern Recognition · Computer Science 2022-07-12 Ting Yao , Yingwei Pan , Yehao Li , Chong-Wah Ngo , Tao Mei

Recent self-supervised learning (SSL) methods have shown impressive results in learning visual representations from unlabeled images. This paper aims to improve their performance further by utilizing the architectural advantages of the…

Computer Vision and Pattern Recognition · Computer Science 2022-07-20 Sukmin Yun , Hankook Lee , Jaehyung Kim , Jinwoo Shin

Vision Transformers (ViTs) enabled the use of the transformer architecture on vision tasks showing impressive performances when trained on big datasets. However, on relatively small datasets, ViTs are less accurate given their lack of…

Computer Vision and Pattern Recognition · Computer Science 2022-10-14 Guglielmo Camporese , Elena Izzo , Lamberto Ballan

In this paper, we present a comparative analysis of various self-supervised Vision Transformers (ViTs), focusing on their local representative power. Inspired by large language models, we examine the abilities of ViTs to perform various…

Computer Vision and Pattern Recognition · Computer Science 2024-03-22 Ani Vanyan , Alvard Barseghyan , Hakob Tamazyan , Vahan Huroyan , Hrant Khachatrian , Martin Danelljan

Vision Transformers (ViT)s have shown great performance in self-supervised learning of global and local representations that can be transferred to downstream applications. Inspired by these results, we introduce a novel self-supervised…

Computer Vision and Pattern Recognition · Computer Science 2022-03-29 Yucheng Tang , Dong Yang , Wenqi Li , Holger Roth , Bennett Landman , Daguang Xu , Vishwesh Nath , Ali Hatamizadeh

Pre-training has marked numerous state of the arts in high-level computer vision, while few attempts have ever been made to investigate how pre-training acts in image processing systems. In this paper, we tailor transformer-based…

Computer Vision and Pattern Recognition · Computer Science 2022-03-22 Wenbo Li , Xin Lu , Shengju Qian , Jiangbo Lu , Xiangyu Zhang , Jiaya Jia

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 have become one of the most important models for computer vision tasks. Although they outperform prior works, they require heavy computational resources on a scale that is quadratic to the number of tokens, $N$. This is…

Computer Vision and Pattern Recognition · Computer Science 2022-05-30 Jeonggeun Song , Heung-Chang Lee

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 Transformer (ViT) has prevailed in computer vision tasks due to its strong long-range dependency modelling ability. \textcolor{blue}{However, its large model size and weak local feature modeling ability hinder its application in real…

Computer Vision and Pattern Recognition · Computer Science 2025-09-12 Yi Zhang , Lingxiao Wei , Bowei Zhang , Ziwei Liu , Kai Yi , Shu Hu