Lightweight High-Precision Monitoring of Damage Locations in Dunhuang Murals Based on Improved YOLACT

Lightweight High-Precision Monitoring of Damage Locations in Dunhuang Murals Based on Improved YOLACT | 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 Lightweight High-Precision Monitoring of Damage Locations in Dunhuang Murals Based on Improved YOLACT Ting Zou, Yiqing Li, Yihan Dong, Jialin An This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7132221/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 19 Nov, 2025 Read the published version in Scientific Reports → Version 1 posted 12 You are reading this latest preprint version Abstract As an important cultural heritage of China and a world treasure, the Dunhuang murals have undergone thousands of years of weathering, oxidation, and human interference, resulting in extensive damage such as cracks, peeling, and fading on their surfaces. Additionally, due to their complex colour palette, it is challenging to quickly identify damaged areas, leading to a situation where the rate of damage to the Dunhuang murals far exceeds the rate of restoration. To achieve efficient and precise monitoring of damage to Dunhuang murals and support cultural heritage preservation efforts, this paper proposes an improved lightweight, high-precision method for monitoring the location of damage to Dunhuang murals based on YOLACT. First, addressing the limitation of traditional YOLACT models in extracting fine-grained texture features, a residual self-attention mechanism capable of extracting global features is introduced to enhance the model's feature extraction capability (mAP50: 79.2064 $%$). Subsequently, by introducing a depth-separable convolutional architecture, the goal of lightweight design is achieved while maintaining high accuracy (parameter count: 715.12 k, floating-point operations: 70.219 M). Finally, to validate the model's effectiveness, this paper conducted validation on a public dataset. Experimental results show that, compared to three mainstream models, the proposed method achieves the highest mAP50 and the smallest parameter count and floating-point operations. Physical sciences/Engineering Physical sciences/Mathematics and computing Dunhuang Murals YOLACT Depth Separable Convolutions Lightweight High Accuracy Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 19 Nov, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 23 Sep, 2025 Reviews received at journal 15 Sep, 2025 Reviews received at journal 04 Sep, 2025 Reviewers agreed at journal 22 Aug, 2025 Reviewers agreed at journal 20 Aug, 2025 Reviews received at journal 18 Aug, 2025 Reviewers agreed at journal 18 Aug, 2025 Reviewers invited by journal 18 Aug, 2025 Editor assigned by journal 18 Aug, 2025 Editor invited by journal 25 Jul, 2025 Submission checks completed at journal 24 Jul, 2025 First submitted to journal 24 Jul, 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-7132221","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":504266371,"identity":"e141cb2a-0cae-4472-a9ad-a9fffbb04830","order_by":0,"name":"Ting Zou","email":"data:image/png;base64,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","orcid":"","institution":"City University of Hong Kong","correspondingAuthor":true,"prefix":"","firstName":"Ting","middleName":"","lastName":"Zou","suffix":""},{"id":504266372,"identity":"752760a5-3557-4f07-8b9d-531fff6c34a3","order_by":1,"name":"Yiqing Li","email":"","orcid":"","institution":"Shenyang Normal University","correspondingAuthor":false,"prefix":"","firstName":"Yiqing","middleName":"","lastName":"Li","suffix":""},{"id":504266373,"identity":"7b81ef5e-beee-4c69-8a2c-934578670522","order_by":2,"name":"Yihan Dong","email":"","orcid":"","institution":"Northeastern University","correspondingAuthor":false,"prefix":"","firstName":"Yihan","middleName":"","lastName":"Dong","suffix":""},{"id":504266374,"identity":"1aed6d31-9c27-48de-b2b9-778f0ecb76bf","order_by":3,"name":"Jialin An","email":"","orcid":"","institution":"Northeastern University","correspondingAuthor":false,"prefix":"","firstName":"Jialin","middleName":"","lastName":"An","suffix":""}],"badges":[],"createdAt":"2025-07-15 15:38:10","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7132221/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7132221/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-24560-0","type":"published","date":"2025-11-19T15:57:05+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":96649991,"identity":"937f0e90-2ff6-48e3-ba85-b9f5a9d507db","added_by":"auto","created_at":"2025-11-24 16:03:35","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1311855,"visible":true,"origin":"","legend":"","description":"","filename":"LightweightHighPrecisionMonitoringofDamageLocationsinDunhuangMuralsBasedonImprovedYOLACT.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7132221/v1_covered_66bd7d47-6428-4807-9bb0-0a2e2fc29402.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Lightweight High-Precision Monitoring of Damage Locations in Dunhuang Murals Based on Improved YOLACT","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"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":"Dunhuang Murals, YOLACT, Depth Separable Convolutions, Lightweight, High Accuracy","lastPublishedDoi":"10.21203/rs.3.rs-7132221/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7132221/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"As an important cultural heritage of China and a world treasure, the Dunhuang murals have undergone thousands of years of weathering, oxidation, and human interference, resulting in extensive damage such as cracks, peeling, and fading on their surfaces. Additionally, due to their complex colour palette, it is challenging to quickly identify damaged areas, leading to a situation where the rate of damage to the Dunhuang murals far exceeds the rate of restoration. To achieve efficient and precise monitoring of damage to Dunhuang murals and support cultural heritage preservation efforts, this paper proposes an improved lightweight, high-precision method for monitoring the location of damage to Dunhuang murals based on YOLACT. First, addressing the limitation of traditional YOLACT models in extracting fine-grained texture features, a residual self-attention mechanism capable of extracting global features is introduced to enhance the model's feature extraction capability (mAP50: 79.2064 $\\%$). Subsequently, by introducing a depth-separable convolutional architecture, the goal of lightweight design is achieved while maintaining high accuracy (parameter count: 715.12 k, floating-point operations: 70.219 M). Finally, to validate the model's effectiveness, this paper conducted validation on a public dataset. Experimental results show that, compared to three mainstream models, the proposed method achieves the highest mAP50 and the smallest parameter count and floating-point operations.","manuscriptTitle":"Lightweight High-Precision Monitoring of Damage Locations in Dunhuang Murals Based on Improved YOLACT","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-26 15:27:32","doi":"10.21203/rs.3.rs-7132221/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-09-23T18:18:10+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-15T06:10:51+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-04T11:22:04+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"150581673335053807472661533225275185484","date":"2025-08-22T14:15:50+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"97180062026370366372659368291527314280","date":"2025-08-20T11:48:43+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-08-19T03:25:24+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"269336253477916403817894815182197945777","date":"2025-08-19T03:18:06+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-08-18T22:23:35+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-08-18T22:21:19+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-07-25T17:11:46+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-07-24T18:24:11+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-07-24T18:21:48+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":"b5c1df17-48b1-40e1-bcc6-a0b05547bad8","owner":[],"postedDate":"August 26th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":53578277,"name":"Physical sciences/Engineering"},{"id":53578278,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2025-11-24T15:59:56+00:00","versionOfRecord":{"articleIdentity":"rs-7132221","link":"https://doi.org/10.1038/s41598-025-24560-0","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-11-19 15:57:05","publishedOnDateReadable":"November 19th, 2025"},"versionCreatedAt":"2025-08-26 15:27:32","video":"","vorDoi":"10.1038/s41598-025-24560-0","vorDoiUrl":"https://doi.org/10.1038/s41598-025-24560-0","workflowStages":[]},"version":"v1","identity":"rs-7132221","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7132221","identity":"rs-7132221","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}