MIAC-Flow: Multi-level Interactive Affine Coupling Flow withFrequency-Spatial Cooperative Attention for Industrial Anomaly Detection

preprint OA: closed
Full text JSON View at publisher
Full text 12,847 characters · extracted from preprint-html · click to expand
MIAC-Flow: Multi-level Interactive Affine Coupling Flow withFrequency-Spatial Cooperative Attention for Industrial Anomaly Detection | 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 Article MIAC-Flow: Multi-level Interactive Affine Coupling Flow withFrequency-Spatial Cooperative Attention for Industrial Anomaly Detection Yueyang Sui, Anluo Yi, Yi Zhao, Zhiyu Zhu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7958772/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 9 You are reading this latest preprint version Abstract To address the limitations of conventional unsupervised defect detection methods, especially their weak cross-scale feature integration and limited ability to capture high-frequency patterns, we propose a novel Multi-level Interactive Affine Coupling Flow (MIAC-Flow). The model achieves competitive performance through the following key innovations: First, a Multi-level Interactive Affine Coupling Layer (MIACL) is designed, which effectively realizes cross-scale feature fusion through hierarchical feature interaction mechanisms. Second, a novel Frequency-Spatial Cooperative Attention Module (FSCAM) is introduced, which significantly enhances the model's capability to represent high-frequency features by jointly optimizing feature representations in both frequency and spatial domains. Our experiments on the MVTec AD dataset show that the proposed model attains top-tier anomaly detection results, reaching an average Image-AUROC score of 98.77% and outperforming current approaches. Systematic ablation studies confirm the synergistic effects of the MIACL and FSCAM modules. Furthermore, extensive experiments across multiple industrial datasets validate the model's superior robustness and generalization capability in complex industrial scenarios, providing a novel solution for industrial defect detection. Physical sciences/Engineering Physical sciences/Mathematics and computing Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 16 Dec, 2025 Reviews received at journal 30 Nov, 2025 Reviewers agreed at journal 24 Nov, 2025 Reviews received at journal 07 Nov, 2025 Reviewers agreed at journal 06 Nov, 2025 Reviewers invited by journal 06 Nov, 2025 Editor assigned by journal 06 Nov, 2025 Submission checks completed at journal 31 Oct, 2025 First submitted to journal 31 Oct, 2025 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-7958772","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":545986964,"identity":"897663f8-0ca9-4126-8996-c53e38623e1d","order_by":0,"name":"Yueyang Sui","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABEUlEQVRIie3QMUvDQBTA8XccXByeZE0J+BkuBAqiNF8lIeAUBBEkUz0InEvB9Qp+CD/ClUC7FF0tdUgXuzhksk7itR3E4WJHh/uPx/24dw/A5fqH+X41aVr+dcI88XMadJGemuaRKnXsoyY7hH8Rrot+eDTX2VilBxLQmodEvpLHxXrdEDlMEqCTJcLg0iZIJdL4Sr5RviwiQWSdjYDlZwj5tY1Q80w+lpQZQgzRKQL2QwSdCQthkIn6WFLki9lKbAdD8D86iZmAVDivg56C7WCUjABZJwmCKSWqvOA+FpFKn8xfahafPvDcSpLn+81ny89vpTdr2vZmmHh31erlvRxYye/S/UZM/KD7LpfL5bL0DcZaWR1Guu0VAAAAAElFTkSuQmCC","orcid":"","institution":"University of Shanghai for Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Yueyang","middleName":"","lastName":"Sui","suffix":""},{"id":545986965,"identity":"c2663ba7-78dc-42ee-b6ac-35f242b82fdf","order_by":1,"name":"Anluo Yi","email":"","orcid":"","institution":"University of Shanghai for Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Anluo","middleName":"","lastName":"Yi","suffix":""},{"id":545986966,"identity":"11372008-c9a6-44d2-ad34-7921a91b6471","order_by":2,"name":"Yi Zhao","email":"","orcid":"","institution":"University of Shanghai for Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Yi","middleName":"","lastName":"Zhao","suffix":""},{"id":545986967,"identity":"c95c47aa-4c25-4df3-b021-13fd7b7ae466","order_by":3,"name":"Zhiyu Zhu","email":"","orcid":"","institution":"University of Shanghai for Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Zhiyu","middleName":"","lastName":"Zhu","suffix":""}],"badges":[],"createdAt":"2025-10-27 12:37:58","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7958772/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7958772/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":96137926,"identity":"d00b7732-3dda-43f2-a6a6-f46f352515c9","added_by":"auto","created_at":"2025-11-18 04:35:29","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5548,"visible":true,"origin":"","legend":"","description":"","filename":"3ed345b25b794fabb105d12cabf48df3.json","url":"https://assets-eu.researchsquare.com/files/rs-7958772/v1/e121be4723eb9bc7bda7d898.json"},{"id":96251285,"identity":"72a633ce-978f-406a-b84f-d905cc6daa78","added_by":"auto","created_at":"2025-11-19 07:39:36","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1023822,"visible":true,"origin":"","legend":"","description":"","filename":"MIACFlow.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7958772/v1_covered_866b0df1-d042-4c36-b037-97f1b8fe6fce.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003eMIAC-Flow: Multi-level Interactive Affine Coupling Flow withFrequency-Spatial Cooperative Attention for Industrial Anomaly Detection\u003c/p\u003e","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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-7958772/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7958772/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"To address the limitations of conventional unsupervised defect detection methods, especially their weak cross-scale feature integration and limited ability to capture high-frequency patterns, we propose a novel Multi-level Interactive Affine Coupling Flow (MIAC-Flow). The model achieves competitive performance through the following key innovations: First, a Multi-level Interactive Affine Coupling Layer (MIACL) is designed, which effectively realizes cross-scale feature fusion through hierarchical feature interaction mechanisms. Second, a novel Frequency-Spatial Cooperative Attention Module (FSCAM) is introduced, which significantly enhances the model's capability to represent high-frequency features by jointly optimizing feature representations in both frequency and spatial domains. Our experiments on the MVTec AD dataset show that the proposed model attains top-tier anomaly detection results, reaching an average Image-AUROC score of 98.77\\% and outperforming current approaches. Systematic ablation studies confirm the synergistic effects of the MIACL and FSCAM modules. Furthermore, extensive experiments across multiple industrial datasets validate the model's superior robustness and generalization capability in complex industrial scenarios, providing a novel solution for industrial defect detection.","manuscriptTitle":"MIAC-Flow: Multi-level Interactive Affine Coupling Flow withFrequency-Spatial Cooperative Attention for Industrial Anomaly Detection","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-18 04:35:24","doi":"10.21203/rs.3.rs-7958772/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-12-16T05:52:51+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-01T01:21:34+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"251646907163279652013105499333177015721","date":"2025-11-24T05:42:13+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-07T08:43:14+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"108349836684400870756585683715655394626","date":"2025-11-07T03:43:36+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-11-07T03:41:39+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-11-06T11:31:39+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-10-31T13:55:38+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-10-31T13:53:59+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"57582d3e-bb6d-48c0-b651-dc53d139f810","owner":[],"postedDate":"November 18th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[{"id":58154443,"name":"Physical sciences/Engineering"},{"id":58154444,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-04-01T17:39:05+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-18 04:35:24","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7958772","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7958772","identity":"rs-7958772","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.

My notes (saved in your browser only)

Ask this paper AI returns verbatim quotes from the full text · source: preprint-html

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2025) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

europepmc
last seen: 2026-05-20T01:45:00.602351+00:00