Towards Robust Industrial Micro-Defect Detection: AContext-Aware and Feature-Refined Architecture forCamouflaged Anomalies

Towards Robust Industrial Micro-Defect Detection: AContext-Aware and Feature-Refined Architecture forCamouflaged Anomalies | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Towards Robust Industrial Micro-Defect Detection: AContext-Aware and Feature-Refined Architecture forCamouflaged Anomalies Xinda Yu, Kunxin Zheng, Chunan Yu, Qingbo Song, Hao Xiao, Ying Zang, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8859645/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 7 You are reading this latest preprint version Abstract Automated detection of surface micro-defects on industrial components, such as copper tubes, is critically important for quality assurance but remains challenging due to the minute scale of anomalies and their visual camouflage against complex backgrounds. These factors lead to weak feature representations and high rates of false positives and missed detections. To address these issues, we propose a novel real-time detection framework designed for efficient context perception and feature refinement. Our method integrates a Context-Perception Aggregation Module (CPAM), which synergises large-kernel perception for macro-texture context and small-kernel aggregation for sharp boundary delineation, effectively breaking the background camouflage. Furthermore, a Feature Additive Refinement Module (FARM) employs a linear-complexity additive token mixer to globally verify and refine the representation of fine-grained anomalies, suppressing noise-induced errors. To support research in this domain, we introduce the Copper Tube Defect Dataset (CTDD), a large-scale, annotated benchmark. Extensive experiments demonstrate that our detector achieves state-of-the-art performance on CTDD, surpassing strong baselines like YOLOv11 by margins of 2.2% in mAP@50 and 3.9% in Precision, while maintaining real-time inference speed. This work provides a robust and efficient solution for high-precision industrial inspection, bridging the gap between contextual understanding and detailed feature analysis. Our code and model are available at: https://github.com/Yu-Xinda/CF-YOLO-A-Context-Aware-and-Feature-Refined-Architecture-for-Camouflaged-Anomalies Object Detection Industrial Defect Detection Feature Refinement Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 09 May, 2026 Reviewers agreed at journal 08 May, 2026 Reviewers agreed at journal 28 Apr, 2026 Reviewers invited by journal 05 Mar, 2026 Editor assigned by journal 13 Feb, 2026 Submission checks completed at journal 13 Feb, 2026 First submitted to journal 12 Feb, 2026 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-8859645","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":601675131,"identity":"1cc9a1f7-e6d2-4d98-9e4d-6be4c7c6e51d","order_by":0,"name":"Xinda Yu","email":"","orcid":"","institution":"Huzhou University","correspondingAuthor":false,"prefix":"","firstName":"Xinda","middleName":"","lastName":"Yu","suffix":""},{"id":601675132,"identity":"66fa833c-cd72-496c-ad5a-2daec6317d20","order_by":1,"name":"Kunxin Zheng","email":"","orcid":"","institution":"Huzhou University","correspondingAuthor":false,"prefix":"","firstName":"Kunxin","middleName":"","lastName":"Zheng","suffix":""},{"id":601675133,"identity":"04d5a619-4447-4e4a-9095-3cee42b989e1","order_by":2,"name":"Chunan Yu","email":"","orcid":"","institution":"Nanjing University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Chunan","middleName":"","lastName":"Yu","suffix":""},{"id":601675134,"identity":"3a2063f0-da17-4c13-8657-92b62f5cc255","order_by":3,"name":"Qingbo Song","email":"","orcid":"","institution":"Huzhou University","correspondingAuthor":false,"prefix":"","firstName":"Qingbo","middleName":"","lastName":"Song","suffix":""},{"id":601675135,"identity":"1930c241-d199-42da-8a51-29774b000df8","order_by":4,"name":"Hao Xiao","email":"","orcid":"","institution":"Huzhou University","correspondingAuthor":false,"prefix":"","firstName":"Hao","middleName":"","lastName":"Xiao","suffix":""},{"id":601675136,"identity":"0870e452-5429-43d1-9fce-1d4864303db2","order_by":5,"name":"Ying Zang","email":"","orcid":"","institution":"Huzhou University","correspondingAuthor":false,"prefix":"","firstName":"Ying","middleName":"","lastName":"Zang","suffix":""},{"id":601675137,"identity":"1a7466a2-2785-4365-9c4c-0de79e41a7bc","order_by":6,"name":"Jie Liu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA4UlEQVRIie2RsQrCMBCGTwJxCXatiD7DSaAu4rNUhLh27CBYKDjaWfAhCoLzSUGXgi/gUBA6+QBO1dY6Nx0F8y1/CP9HjguAwfCD9BgAulCMLABVXXQCncJrhWQ/aK3UQfOY6nMLpSvQy/xb53Cl/C5gOoyJ5VnzYALRTXPmEC2lACVj4hPUKvMN484pUAMBSTmh4LZeKZiQIVTKq60SJDbyj0JtFO6he1Zop6D6e1zIXcKdRsWykuP4uZquoyhV9sOfDbeXMG9Uqoe++xFu+atlMk2/qmR1dknfNRgMhr/kDTQNQRqwsCCUAAAAAElFTkSuQmCC","orcid":"","institution":"Huzhou University","correspondingAuthor":true,"prefix":"","firstName":"Jie","middleName":"","lastName":"Liu","suffix":""}],"badges":[],"createdAt":"2026-02-12 08:39:18","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8859645/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8859645/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104416846,"identity":"f35b8e24-8ce3-4398-8f9f-0f0cb3bd3cdb","added_by":"auto","created_at":"2026-03-11 13:17:03","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":7419064,"visible":true,"origin":"","legend":"","description":"","filename":"source.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8859645/v1_covered_7c2b5372-41ab-4dc2-86bf-db502803636b.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Towards Robust Industrial Micro-Defect Detection: AContext-Aware and Feature-Refined Architecture forCamouflaged Anomalies","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"the-visual-computer","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"tvcj","sideBox":"Learn more about [The Visual Computer](http://link.springer.com/journal/371)","snPcode":"371","submissionUrl":"https://submission.nature.com/new-submission/371/3","title":"The Visual Computer","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Object Detection, Industrial Defect Detection, Feature Refinement","lastPublishedDoi":"10.21203/rs.3.rs-8859645/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8859645/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Automated detection of surface micro-defects on industrial components, such as copper tubes, is critically important for quality assurance but remains challenging due to the minute scale of anomalies and their visual camouflage against complex backgrounds. These factors lead to weak feature representations and high rates of false positives and missed detections. To address these issues, we propose a novel real-time detection framework designed for efficient context perception and feature refinement. Our method integrates a Context-Perception Aggregation Module (CPAM), which synergises large-kernel perception for macro-texture context and small-kernel aggregation for sharp boundary delineation, effectively breaking the background camouflage. Furthermore, a Feature Additive Refinement Module (FARM) employs a linear-complexity additive token mixer to globally verify and refine the representation of fine-grained anomalies, suppressing noise-induced errors. To support research in this domain, we introduce the Copper Tube Defect Dataset (CTDD), a large-scale, annotated benchmark. Extensive experiments demonstrate that our detector achieves state-of-the-art performance on CTDD, surpassing strong baselines like YOLOv11 by margins of 2.2% in mAP@50 and 3.9% in Precision, while maintaining real-time inference speed. This work provides a robust and efficient solution for high-precision industrial inspection, bridging the gap between contextual understanding and detailed feature analysis. Our code and model are available at: https://github.com/Yu-Xinda/CF-YOLO-A-Context-Aware-and-Feature-Refined-Architecture-for-Camouflaged-Anomalies","manuscriptTitle":"Towards Robust Industrial Micro-Defect Detection: AContext-Aware and Feature-Refined Architecture forCamouflaged Anomalies","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-11 12:54:02","doi":"10.21203/rs.3.rs-8859645/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-05-09T12:56:35+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"310128414290544051020826219285092487066","date":"2026-05-08T06:01:28+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"307267722396428606681994986008395566359","date":"2026-04-29T00:12:04+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-03-05T16:33:20+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-02-14T00:24:08+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-02-13T07:49:31+00:00","index":"","fulltext":""},{"type":"submitted","content":"The Visual Computer","date":"2026-02-12T08:26:21+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"the-visual-computer","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"tvcj","sideBox":"Learn more about [The Visual Computer](http://link.springer.com/journal/371)","snPcode":"371","submissionUrl":"https://submission.nature.com/new-submission/371/3","title":"The Visual Computer","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"b2de6a33-c88b-4bb6-94cc-5637055fb64e","owner":[],"postedDate":"March 11th, 2026","published":true,"recentEditorialEvents":[{"type":"editorInvitedReview","content":"","date":"2026-05-09T12:56:35+00:00","index":39,"fulltext":""},{"type":"reviewerAgreed","content":"310128414290544051020826219285092487066","date":"2026-05-08T06:01:28+00:00","index":38,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-03-11T12:54:02+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-11 12:54:02","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8859645","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8859645","identity":"rs-8859645","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}