视觉表征的高效和有效的自监督学习

Sravanti Addepalli, K. Bhogale, P. Dey, R. Venkatesh Babu
{"title":"视觉表征的高效和有效的自监督学习","authors":"Sravanti Addepalli, K. Bhogale, P. Dey, R. Venkatesh Babu","doi":"10.48550/arXiv.2210.09866","DOIUrl":null,"url":null,"abstract":"Self-supervision has emerged as a propitious method for visual representation learning after the recent paradigm shift from handcrafted pretext tasks to instance-similarity based approaches. Most state-of-the-art methods enforce similarity between various augmentations of a given image, while some methods additionally use contrastive approaches to explicitly ensure diverse representations. While these approaches have indeed shown promising direction, they require a significantly larger number of training iterations when compared to the supervised counterparts. In this work, we explore reasons for the slow convergence of these methods, and further propose to strengthen them using well-posed auxiliary tasks that converge significantly faster, and are also useful for representation learning. The proposed method utilizes the task of rotation prediction to improve the efficiency of existing state-of-the-art methods. We demonstrate significant gains in performance using the proposed method on multiple datasets, specifically for lower training epochs.","PeriodicalId":72676,"journal":{"name":"Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision","volume":"43 1","pages":"523-538"},"PeriodicalIF":0.0000,"publicationDate":"2022-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"Towards Efficient and Effective Self-Supervised Learning of Visual Representations\",\"authors\":\"Sravanti Addepalli, K. Bhogale, P. Dey, R. Venkatesh Babu\",\"doi\":\"10.48550/arXiv.2210.09866\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Self-supervision has emerged as a propitious method for visual representation learning after the recent paradigm shift from handcrafted pretext tasks to instance-similarity based approaches. Most state-of-the-art methods enforce similarity between various augmentations of a given image, while some methods additionally use contrastive approaches to explicitly ensure diverse representations. While these approaches have indeed shown promising direction, they require a significantly larger number of training iterations when compared to the supervised counterparts. In this work, we explore reasons for the slow convergence of these methods, and further propose to strengthen them using well-posed auxiliary tasks that converge significantly faster, and are also useful for representation learning. The proposed method utilizes the task of rotation prediction to improve the efficiency of existing state-of-the-art methods. We demonstrate significant gains in performance using the proposed method on multiple datasets, specifically for lower training epochs.\",\"PeriodicalId\":72676,\"journal\":{\"name\":\"Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision\",\"volume\":\"43 1\",\"pages\":\"523-538\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-10-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2210.09866\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2210.09866","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 4

摘要

在最近从手工制作的借口任务到基于实例相似性的方法的范式转变之后,自我监督已经成为视觉表征学习的一种有利方法。大多数最先进的方法在给定图像的各种增强之间强制相似性,而一些方法另外使用对比方法来明确地确保不同的表示。虽然这些方法确实显示出了有希望的方向,但是与有监督的方法相比,它们需要大量的训练迭代。在这项工作中,我们探讨了这些方法收敛缓慢的原因,并进一步提出使用良好定位的辅助任务来加强它们,这些任务的收敛速度要快得多,并且对表示学习也很有用。该方法利用旋转预测任务来提高现有最先进方法的效率。我们证明了在多个数据集上使用所提出的方法在性能上的显着提高,特别是对于较低的训练周期。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Towards Efficient and Effective Self-Supervised Learning of Visual Representations
Self-supervision has emerged as a propitious method for visual representation learning after the recent paradigm shift from handcrafted pretext tasks to instance-similarity based approaches. Most state-of-the-art methods enforce similarity between various augmentations of a given image, while some methods additionally use contrastive approaches to explicitly ensure diverse representations. While these approaches have indeed shown promising direction, they require a significantly larger number of training iterations when compared to the supervised counterparts. In this work, we explore reasons for the slow convergence of these methods, and further propose to strengthen them using well-posed auxiliary tasks that converge significantly faster, and are also useful for representation learning. The proposed method utilizes the task of rotation prediction to improve the efficiency of existing state-of-the-art methods. We demonstrate significant gains in performance using the proposed method on multiple datasets, specifically for lower training epochs.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信