FC2P: Feature Cross-Channel Projection for Unsupervised Anomaly Segmentation

IF 5.9 2区 工程技术 Q1 ENGINEERING, ELECTRICAL & ELECTRONIC
Yichi Chen;Weizhi Xian;Junjie Wang;Xian Tao;Bin Chen
{"title":"FC2P: Feature Cross-Channel Projection for Unsupervised Anomaly Segmentation","authors":"Yichi Chen;Weizhi Xian;Junjie Wang;Xian Tao;Bin Chen","doi":"10.1109/TIM.2025.3608319","DOIUrl":null,"url":null,"abstract":"Unsupervised anomaly segmentation plays a critical role in real-world industrial product quality inspection. While feature reconstruction-based methods have shown promising performance by detecting anomalies through differences between pretrained features and their reconstructions, existing approaches often suffer from shortcut learning, and leading to reconstruction failures and inaccurate anomaly representation across multistage features. To address these limitations, we propose feature cross-channel projection (FC2P), a novel approach for anomaly segmentation. FC2P divides features into two subsets based on neighboring channels and employs two autoencoders for closed-loop prediction, effectively mitigating shortcut effects while capturing semantic relationships for efficient reconstruction. In addition, we introduce an anomaly exposure network (AExNet), which progressively amplifies anomalies across multistage feature residuals, generating precise anomaly score maps for accurate segmentation. Extensive experiments on MVTec AD and Visa benchmark datasets demonstrate that the proposed FC2P achieves state-of-the-art (SOTA) performance, with average precision (AP) scores of 79.8% and 44.8%, respectively. Moreover, visualization results on real industrial data further show the practicality of our proposed method. The code will be made publicly available at <uri>https://github.com/Karma1628/work-2</uri> to ensure reproducibility and facilitate further research.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-13"},"PeriodicalIF":5.9000,"publicationDate":"2025-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Instrumentation and Measurement","FirstCategoryId":"5","ListUrlMain":"https://ieeexplore.ieee.org/document/11155879/","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0

Abstract

Unsupervised anomaly segmentation plays a critical role in real-world industrial product quality inspection. While feature reconstruction-based methods have shown promising performance by detecting anomalies through differences between pretrained features and their reconstructions, existing approaches often suffer from shortcut learning, and leading to reconstruction failures and inaccurate anomaly representation across multistage features. To address these limitations, we propose feature cross-channel projection (FC2P), a novel approach for anomaly segmentation. FC2P divides features into two subsets based on neighboring channels and employs two autoencoders for closed-loop prediction, effectively mitigating shortcut effects while capturing semantic relationships for efficient reconstruction. In addition, we introduce an anomaly exposure network (AExNet), which progressively amplifies anomalies across multistage feature residuals, generating precise anomaly score maps for accurate segmentation. Extensive experiments on MVTec AD and Visa benchmark datasets demonstrate that the proposed FC2P achieves state-of-the-art (SOTA) performance, with average precision (AP) scores of 79.8% and 44.8%, respectively. Moreover, visualization results on real industrial data further show the practicality of our proposed method. The code will be made publicly available at https://github.com/Karma1628/work-2 to ensure reproducibility and facilitate further research.
FC2P:特征跨通道投影的无监督异常分割
无监督异常分割在实际工业产品质量检测中起着至关重要的作用。虽然基于特征重构的方法通过预训练特征与重建特征之间的差异来检测异常,显示出了良好的性能,但现有的方法往往存在快速学习的问题,导致重建失败和跨多阶段特征的不准确异常表示。为了解决这些限制,我们提出了一种新的异常分割方法——特征跨通道投影(FC2P)。FC2P基于相邻信道将特征划分为两个子集,采用两个自编码器进行闭环预测,在捕获语义关系的同时有效缓解了捷径效应,实现了高效重构。此外,我们引入了一种异常暴露网络(AExNet),该网络在多阶段特征残差中逐步放大异常,生成精确的异常评分图,用于准确分割。在MVTec AD和Visa基准数据集上的大量实验表明,所提出的FC2P达到了最先进(SOTA)的性能,平均精度(AP)分别为79.8%和44.8%。在实际工业数据上的可视化结果进一步证明了本文方法的实用性。该代码将在https://github.com/Karma1628/work-2上公开,以确保可重复性并促进进一步的研究。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
IEEE Transactions on Instrumentation and Measurement
IEEE Transactions on Instrumentation and Measurement 工程技术-工程:电子与电气
CiteScore
9.00
自引率
23.20%
发文量
1294
审稿时长
3.9 months
期刊介绍: Papers are sought that address innovative solutions to the development and use of electrical and electronic instruments and equipment to measure, monitor and/or record physical phenomena for the purpose of advancing measurement science, methods, functionality and applications. The scope of these papers may encompass: (1) theory, methodology, and practice of measurement; (2) design, development and evaluation of instrumentation and measurement systems and components used in generating, acquiring, conditioning and processing signals; (3) analysis, representation, display, and preservation of the information obtained from a set of measurements; and (4) scientific and technical support to establishment and maintenance of technical standards in the field of Instrumentation and Measurement.
×
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:604180095
Book学术官方微信