自适应 Hypersphere 数据描述,用于少量单类分类

IF 3.4 2区 计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Applied Intelligence Pub Date : 2024-10-07 DOI:10.1007/s10489-024-05836-w
Yuchen Ren, Xiabi Liu, Liyuan Pan, Lijuan Niu
{"title":"自适应 Hypersphere 数据描述,用于少量单类分类","authors":"Yuchen Ren,&nbsp;Xiabi Liu,&nbsp;Liyuan Pan,&nbsp;Lijuan Niu","doi":"10.1007/s10489-024-05836-w","DOIUrl":null,"url":null,"abstract":"<p>Few-shot one-class classification (FS-OCC) is an important and challenging problem involving the recognition of a class using a limited number of positive training samples. Data description is essential for solving the FS-OCC problem as it delineates a region that separates positive data from other classes in the feature space. This paper introduces an effective FS-OCC model named Adaptive Hypersphere Data Description (AHDD). AHDD utilizes hypersphere-based data description with a learnable radius to determine the appropriate region for positive samples in the feature space. Both the radius and the feature network are learned concurrently using meta-learning. We propose a loss function for AHDD that enables the mutual adaptation of the radius and feature within a single FS-OCC task. AHDD significantly outperforms other state-of-the-art FS-OCC methods across various benchmarks and demonstrates strong performance on test sets with extreme class imbalance rates. Experimental results indicate that AHDD learns a robust feature representation, and the implementation of an adaptive radius can also improve the existing FS-OCC baselines.</p>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"54 24","pages":"12885 - 12897"},"PeriodicalIF":3.4000,"publicationDate":"2024-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Adaptive Hypersphere Data Description for few-shot one-class classification\",\"authors\":\"Yuchen Ren,&nbsp;Xiabi Liu,&nbsp;Liyuan Pan,&nbsp;Lijuan Niu\",\"doi\":\"10.1007/s10489-024-05836-w\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Few-shot one-class classification (FS-OCC) is an important and challenging problem involving the recognition of a class using a limited number of positive training samples. Data description is essential for solving the FS-OCC problem as it delineates a region that separates positive data from other classes in the feature space. This paper introduces an effective FS-OCC model named Adaptive Hypersphere Data Description (AHDD). AHDD utilizes hypersphere-based data description with a learnable radius to determine the appropriate region for positive samples in the feature space. Both the radius and the feature network are learned concurrently using meta-learning. We propose a loss function for AHDD that enables the mutual adaptation of the radius and feature within a single FS-OCC task. AHDD significantly outperforms other state-of-the-art FS-OCC methods across various benchmarks and demonstrates strong performance on test sets with extreme class imbalance rates. Experimental results indicate that AHDD learns a robust feature representation, and the implementation of an adaptive radius can also improve the existing FS-OCC baselines.</p>\",\"PeriodicalId\":8041,\"journal\":{\"name\":\"Applied Intelligence\",\"volume\":\"54 24\",\"pages\":\"12885 - 12897\"},\"PeriodicalIF\":3.4000,\"publicationDate\":\"2024-10-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Applied Intelligence\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://link.springer.com/article/10.1007/s10489-024-05836-w\",\"RegionNum\":2,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Applied Intelligence","FirstCategoryId":"94","ListUrlMain":"https://link.springer.com/article/10.1007/s10489-024-05836-w","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

摘要

少量单类分类(FS-OCC)是一个重要而具有挑战性的问题,它涉及使用有限数量的正向训练样本来识别一个类别。数据描述对于解决 FS-OCC 问题至关重要,因为它能在特征空间中划分出一个区域,将正向数据与其他类别数据区分开来。本文介绍了一种有效的 FS-OCC 模型,名为自适应超球数据描述(AHDD)。AHDD 利用基于超球的数据描述和可学习半径来确定特征空间中阳性样本的适当区域。半径和特征网络通过元学习同时学习。我们为 AHDD 提出了一种损失函数,可在单个 FS-OCC 任务中实现半径和特征的相互适应。在各种基准测试中,AHDD 的表现明显优于其他最先进的 FS-OCC 方法,并在具有极端类不平衡率的测试集上表现出强劲的性能。实验结果表明,AHDD 可以学习稳健的特征表示,自适应半径的实现也可以改进现有的 FS-OCC 基线。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

摘要图片

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Adaptive Hypersphere Data Description for few-shot one-class classification

Few-shot one-class classification (FS-OCC) is an important and challenging problem involving the recognition of a class using a limited number of positive training samples. Data description is essential for solving the FS-OCC problem as it delineates a region that separates positive data from other classes in the feature space. This paper introduces an effective FS-OCC model named Adaptive Hypersphere Data Description (AHDD). AHDD utilizes hypersphere-based data description with a learnable radius to determine the appropriate region for positive samples in the feature space. Both the radius and the feature network are learned concurrently using meta-learning. We propose a loss function for AHDD that enables the mutual adaptation of the radius and feature within a single FS-OCC task. AHDD significantly outperforms other state-of-the-art FS-OCC methods across various benchmarks and demonstrates strong performance on test sets with extreme class imbalance rates. Experimental results indicate that AHDD learns a robust feature representation, and the implementation of an adaptive radius can also improve the existing FS-OCC baselines.

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
Applied Intelligence
Applied Intelligence 工程技术-计算机:人工智能
CiteScore
6.60
自引率
20.80%
发文量
1361
审稿时长
5.9 months
期刊介绍: With a focus on research in artificial intelligence and neural networks, this journal addresses issues involving solutions of real-life manufacturing, defense, management, government and industrial problems which are too complex to be solved through conventional approaches and require the simulation of intelligent thought processes, heuristics, applications of knowledge, and distributed and parallel processing. The integration of these multiple approaches in solving complex problems is of particular importance. The journal presents new and original research and technological developments, addressing real and complex issues applicable to difficult problems. It provides a medium for exchanging scientific research and technological achievements accomplished by the international community.
期刊最新文献
ZPDSN: spatio-temporal meteorological forecasting with topological data analysis DTR4Rec: direct transition relationship for sequential recommendation Unsupervised anomaly detection and imputation in noisy time series data for enhancing load forecasting A prototype evolution network for relation extraction Highway spillage detection using an improved STPM anomaly detection network from a surveillance perspective
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1