Enhancing out-of-distribution detection via diversified multi-prototype contrastive learning

IF 7.5 1区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Yulong Jia , Jiaming Li , Ganlong Zhao , Shuangyin Liu , Weijun Sun , Liang Lin , Guanbin Li
{"title":"Enhancing out-of-distribution detection via diversified multi-prototype contrastive learning","authors":"Yulong Jia ,&nbsp;Jiaming Li ,&nbsp;Ganlong Zhao ,&nbsp;Shuangyin Liu ,&nbsp;Weijun Sun ,&nbsp;Liang Lin ,&nbsp;Guanbin Li","doi":"10.1016/j.patcog.2024.111214","DOIUrl":null,"url":null,"abstract":"<div><div>Detecting out-of-distribution (OOD) inputs is critical for safely deploying deep neural networks in the open world. Recent distance-based contrastive learning methods demonstrated their effectiveness by learning improved feature representations in the embedding space. However, those methods might lead to an incomplete and ambiguous representation of a class, thereby resulting in the loss of intra-class semantic information. In this work, we propose a novel diversified multi-prototype contrastive learning framework, which preserves the semantic knowledge within each class’s embedding space by introducing multiple fine-grained prototypes for each class. This preserves intrinsic features within the in-distribution data, promoting discrimination against OOD samples. We also devise an activation constraints technique to mitigate the impact of extreme activation values on other dimensions and facilitate the computation of distance-based scores. Extensive experiments on several benchmarks show that our proposed method is effective and beneficial for OOD detection, outperforming previous state-of-the-art methods.</div></div>","PeriodicalId":49713,"journal":{"name":"Pattern Recognition","volume":"161 ","pages":"Article 111214"},"PeriodicalIF":7.5000,"publicationDate":"2024-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Pattern Recognition","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0031320324009658","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Detecting out-of-distribution (OOD) inputs is critical for safely deploying deep neural networks in the open world. Recent distance-based contrastive learning methods demonstrated their effectiveness by learning improved feature representations in the embedding space. However, those methods might lead to an incomplete and ambiguous representation of a class, thereby resulting in the loss of intra-class semantic information. In this work, we propose a novel diversified multi-prototype contrastive learning framework, which preserves the semantic knowledge within each class’s embedding space by introducing multiple fine-grained prototypes for each class. This preserves intrinsic features within the in-distribution data, promoting discrimination against OOD samples. We also devise an activation constraints technique to mitigate the impact of extreme activation values on other dimensions and facilitate the computation of distance-based scores. Extensive experiments on several benchmarks show that our proposed method is effective and beneficial for OOD detection, outperforming previous state-of-the-art methods.
求助全文
约1分钟内获得全文 求助全文
来源期刊
Pattern Recognition
Pattern Recognition 工程技术-工程:电子与电气
CiteScore
14.40
自引率
16.20%
发文量
683
审稿时长
5.6 months
期刊介绍: The field of Pattern Recognition is both mature and rapidly evolving, playing a crucial role in various related fields such as computer vision, image processing, text analysis, and neural networks. It closely intersects with machine learning and is being applied in emerging areas like biometrics, bioinformatics, multimedia data analysis, and data science. The journal Pattern Recognition, established half a century ago during the early days of computer science, has since grown significantly in scope and influence.
×
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