OOD 检测的最新进展:问题与方法

Shuo Lu, YingSheng Wang, LuJun Sheng, AiHua Zheng, LinXiao He, Jian Liang
{"title":"OOD 检测的最新进展:问题与方法","authors":"Shuo Lu, YingSheng Wang, LuJun Sheng, AiHua Zheng, LinXiao He, Jian Liang","doi":"arxiv-2409.11884","DOIUrl":null,"url":null,"abstract":"Out-of-distribution (OOD) detection aims to detect test samples outside the\ntraining category space, which is an essential component in building reliable\nmachine learning systems. Existing reviews on OOD detection primarily focus on\nmethod taxonomy, surveying the field by categorizing various approaches.\nHowever, many recent works concentrate on non-traditional OOD detection\nscenarios, such as test-time adaptation, multi-modal data sources and other\nnovel contexts. In this survey, we uniquely review recent advances in OOD\ndetection from the problem scenario perspective for the first time. According\nto whether the training process is completely controlled, we divide OOD\ndetection methods into training-driven and training-agnostic. Besides,\nconsidering the rapid development of pre-trained models, large pre-trained\nmodel-based OOD detection is also regarded as an important category and\ndiscussed separately. Furthermore, we provide a discussion of the evaluation\nscenarios, a variety of applications, and several future research directions.\nWe believe this survey with new taxonomy will benefit the proposal of new\nmethods and the expansion of more practical scenarios. A curated list of\nrelated papers is provided in the Github repository:\n\\url{https://github.com/shuolucs/Awesome-Out-Of-Distribution-Detection}","PeriodicalId":501301,"journal":{"name":"arXiv - CS - Machine Learning","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Recent Advances in OOD Detection: Problems and Approaches\",\"authors\":\"Shuo Lu, YingSheng Wang, LuJun Sheng, AiHua Zheng, LinXiao He, Jian Liang\",\"doi\":\"arxiv-2409.11884\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Out-of-distribution (OOD) detection aims to detect test samples outside the\\ntraining category space, which is an essential component in building reliable\\nmachine learning systems. Existing reviews on OOD detection primarily focus on\\nmethod taxonomy, surveying the field by categorizing various approaches.\\nHowever, many recent works concentrate on non-traditional OOD detection\\nscenarios, such as test-time adaptation, multi-modal data sources and other\\nnovel contexts. In this survey, we uniquely review recent advances in OOD\\ndetection from the problem scenario perspective for the first time. According\\nto whether the training process is completely controlled, we divide OOD\\ndetection methods into training-driven and training-agnostic. Besides,\\nconsidering the rapid development of pre-trained models, large pre-trained\\nmodel-based OOD detection is also regarded as an important category and\\ndiscussed separately. Furthermore, we provide a discussion of the evaluation\\nscenarios, a variety of applications, and several future research directions.\\nWe believe this survey with new taxonomy will benefit the proposal of new\\nmethods and the expansion of more practical scenarios. A curated list of\\nrelated papers is provided in the Github repository:\\n\\\\url{https://github.com/shuolucs/Awesome-Out-Of-Distribution-Detection}\",\"PeriodicalId\":501301,\"journal\":{\"name\":\"arXiv - CS - Machine Learning\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Machine Learning\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.11884\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Machine Learning","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.11884","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

分布外(OOD)检测旨在检测训练类别空间之外的测试样本,是构建可靠的机器学习系统的重要组成部分。现有的 OOD 检测综述主要集中在方法分类学方面,通过对各种方法进行分类来对该领域进行调查。然而,最近的许多作品都集中在非传统的 OOD 检测场景上,如测试时间适应、多模式数据源和其他新的背景。在本研究中,我们首次从问题场景的角度独特地回顾了 OOD 检测的最新进展。根据训练过程是否完全可控,我们将 OOD 检测方法分为训练驱动型和训练无关型。此外,考虑到预训练模型的快速发展,基于大型预训练模型的 OOD 检测也被视为一个重要类别,并单独进行了讨论。此外,我们还讨论了评估场景、各种应用以及未来的几个研究方向。我们相信,这份带有新分类法的调查报告将有助于提出新方法和扩展更多实用场景。Github 存储库中提供了相关论文的精选列表:\url{https://github.com/shuolucs/Awesome-Out-Of-Distribution-Detection}。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Recent Advances in OOD Detection: Problems and Approaches
Out-of-distribution (OOD) detection aims to detect test samples outside the training category space, which is an essential component in building reliable machine learning systems. Existing reviews on OOD detection primarily focus on method taxonomy, surveying the field by categorizing various approaches. However, many recent works concentrate on non-traditional OOD detection scenarios, such as test-time adaptation, multi-modal data sources and other novel contexts. In this survey, we uniquely review recent advances in OOD detection from the problem scenario perspective for the first time. According to whether the training process is completely controlled, we divide OOD detection methods into training-driven and training-agnostic. Besides, considering the rapid development of pre-trained models, large pre-trained model-based OOD detection is also regarded as an important category and discussed separately. Furthermore, we provide a discussion of the evaluation scenarios, a variety of applications, and several future research directions. We believe this survey with new taxonomy will benefit the proposal of new methods and the expansion of more practical scenarios. A curated list of related papers is provided in the Github repository: \url{https://github.com/shuolucs/Awesome-Out-Of-Distribution-Detection}
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