FLaNS: Feature-Label Negative Sampling for Out-of-Distribution Detection

IF 3.4 3区 计算机科学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS IEEE Access Pub Date : 2025-03-06 DOI:10.1109/ACCESS.2025.3548702
Chaejin Lim;Junhee Hyeon;Kiseong Lee;Dongil Han
{"title":"FLaNS: Feature-Label Negative Sampling for Out-of-Distribution Detection","authors":"Chaejin Lim;Junhee Hyeon;Kiseong Lee;Dongil Han","doi":"10.1109/ACCESS.2025.3548702","DOIUrl":null,"url":null,"abstract":"Many existing deep learning models suffer from a fundamental limitation, where they often misclassify Out-of-Distribution (OOD) data as In-Distribution (ID) data. OOD data represent data patterns that differ from the training distribution, such as images of unseen classes or different domains. This misclassification occurs because deep learning models are inherently designed to classify inputs into one of their known categories. To address this limitation, we propose Feature-Label Negative Sampling (FLaNS), which exploits the observation that OOD data inherently exhibit mismatches between features and their assigned labels. Our method constructs negative data by deliberately creating feature-label mismatches from ID data, which naturally deviate from the learned ID distribution. These synthetic data enable the Support Vector Machine (SVM) to learn decision boundaries that discriminate between ID and OOD data without requiring actual OOD data during training. We evaluated our method on the NCT-CRC-HE and CIFAR-100 datasets using two backbone models. Our approach demonstrates stable and reliable performance in both Receiver Operating Characteristics (ROC) Curve Area (AUROC) and False Positive Rate at 95% True Positive Rate (FPR95) metrics compared to existing methods. This research enhances OOD detection by introducing a method that leverages feature-label mismatches in ID data, improving detection performance without needing diverse OOD data, which are often difficult to collect.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"43878-43888"},"PeriodicalIF":3.4000,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10915589","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Access","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10915589/","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0

Abstract

Many existing deep learning models suffer from a fundamental limitation, where they often misclassify Out-of-Distribution (OOD) data as In-Distribution (ID) data. OOD data represent data patterns that differ from the training distribution, such as images of unseen classes or different domains. This misclassification occurs because deep learning models are inherently designed to classify inputs into one of their known categories. To address this limitation, we propose Feature-Label Negative Sampling (FLaNS), which exploits the observation that OOD data inherently exhibit mismatches between features and their assigned labels. Our method constructs negative data by deliberately creating feature-label mismatches from ID data, which naturally deviate from the learned ID distribution. These synthetic data enable the Support Vector Machine (SVM) to learn decision boundaries that discriminate between ID and OOD data without requiring actual OOD data during training. We evaluated our method on the NCT-CRC-HE and CIFAR-100 datasets using two backbone models. Our approach demonstrates stable and reliable performance in both Receiver Operating Characteristics (ROC) Curve Area (AUROC) and False Positive Rate at 95% True Positive Rate (FPR95) metrics compared to existing methods. This research enhances OOD detection by introducing a method that leverages feature-label mismatches in ID data, improving detection performance without needing diverse OOD data, which are often difficult to collect.
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
求助全文
约1分钟内获得全文 去求助
来源期刊
IEEE Access
IEEE Access COMPUTER SCIENCE, INFORMATION SYSTEMSENGIN-ENGINEERING, ELECTRICAL & ELECTRONIC
CiteScore
9.80
自引率
7.70%
发文量
6673
审稿时长
6 weeks
期刊介绍: IEEE Access® is a multidisciplinary, open access (OA), applications-oriented, all-electronic archival journal that continuously presents the results of original research or development across all of IEEE''s fields of interest. IEEE Access will publish articles that are of high interest to readers, original, technically correct, and clearly presented. Supported by author publication charges (APC), its hallmarks are a rapid peer review and publication process with open access to all readers. Unlike IEEE''s traditional Transactions or Journals, reviews are "binary", in that reviewers will either Accept or Reject an article in the form it is submitted in order to achieve rapid turnaround. Especially encouraged are submissions on: Multidisciplinary topics, or applications-oriented articles and negative results that do not fit within the scope of IEEE''s traditional journals. Practical articles discussing new experiments or measurement techniques, interesting solutions to engineering. Development of new or improved fabrication or manufacturing techniques. Reviews or survey articles of new or evolving fields oriented to assist others in understanding the new area.
期刊最新文献
High-Performance NTRU Accelerator Using a Direct Memory Access Controller Corrections to “A Visual Prompt-Based Mobile Learning System for Improved Algebraic Understanding in Students With Learning Disabilities” Utility Meets Privacy: A Critical Evaluation of Tabular Data Synthesizers Minimizing Delay at Closely Spaced Signalized Intersections Through Green Time Ratio Optimization: A Hybrid Approach With K-Means Clustering and Genetic Algorithms Analysis and Design of mmWave Passive CMOS Circulators With Unequal Port Impedances
×
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