SAD-ReID: Semantically-Anchored Dynamics for Unsupervised Vehicle Re-Identification

SAD-ReID: Semantically-Anchored Dynamics for Unsupervised Vehicle Re-Identification | 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 SAD-ReID: Semantically-Anchored Dynamics for Unsupervised Vehicle Re-Identification Yun Jiang, Kunyi Zhu, Tao Sun This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9435656/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 5 You are reading this latest preprint version Abstract Unsupervised vehicle re-identification (Re-ID) is pivotal for scalable intelligent transportation systems but faces significant challenges from severe noise accumulation. Traditional clustering-based methods often suffer from error propagation during online training, as purely visual features are highly susceptible to intra-class viewpoint variations and inter-class similarities. To mitigate this fundamental limitation, we propose a novel Semantically-Anchored Dynamics (SAD-ReID) framework that exploits the viewpoint-invariant stability of text-induced semantic knowledge derived from Vision-Language Models. Specifically, we first introduce a Semantically-Guided Initialization strategy that fuses visual similarities with detailed textual descriptions generated automatically by Qwen-VL. This rectifies initial visual clusters to establish robust text-guided dual-prototype (visual and semantic) anchors. During the online learning phase, we propose a Reliability-Aware Dynamic Update (RADU) mechanism. By calculating a Cross-Modality Allegiance (CMA) score that measures the topological agreement between visual and textual spaces, RADU dynamically adjusts the memory update momentum. This efficiently accelerates learning from reliable samples while filtering out noisy pseudo-labels to prevent memory corruption. Furthermore, an Adaptive Granularity Attention Fusion (AGAF) module is designed to capture both global semantic attributes and fine-grained local discriminative details. Extensive experiments on the VeRi-776 and VehicleID benchmarks demonstrate the significant superiority of our approach over existing state-of-the-art methods, achieving an impressive Rank-1 accuracy of 90.0% and 43.2% mAP on VeRi-776. By enforcing text-visual semantic consistency throughout the evolutionary training process, SAD-ReID successfully prevents model drift and learns highly robust representations without any manual annotation. Unsupervised Vehicle Re-ID Vision-Language Models Semantic Guidance Reliability-Aware Learning Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers agreed at journal 27 Apr, 2026 Reviewers invited by journal 27 Apr, 2026 Editor assigned by journal 17 Apr, 2026 Submission checks completed at journal 17 Apr, 2026 First submitted to journal 16 Apr, 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-9435656","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":630658980,"identity":"b7f0c4f2-6013-491b-832c-21b7440d39d7","order_by":0,"name":"Yun Jiang","email":"","orcid":"","institution":"Northwest Normal University","correspondingAuthor":false,"prefix":"","firstName":"Yun","middleName":"","lastName":"Jiang","suffix":""},{"id":630658981,"identity":"d539468e-586f-4bb8-95a1-8d68e700afb7","order_by":1,"name":"Kunyi Zhu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABDklEQVRIie3QMUvDQBTA8QsPzuUgg8srQj/DC4HSIrZf5Y5AnRqULJ2kULgs6hzBD9HR8cJBXQJdC10qrg4BQRQKmlo3TcjocP/hOB7vx8Ex5nL9w3wAQyVht7rk2/Jnik2kk2p5mV30w07KoyBrQ6go6FWUU0Ur0TsWbQhby2AhCCWzfAxnDzYmA/lGsGFcJ7xMRoSEsTeH5fOksAkZHp0KFiV1BFAuiQgTAH4eTvRGLYzonQhm1KyGcFTpuyRUGqrNwTfx3xqJEJaRqcj1nniHV3gjwSPNghlhiFB98o3+VHeWh4N7imrJyPpluNtddUcrm28/9FjdPs6f1i/TYS35I9gf1H7f5XK5XL/7AuDXWFyNANcPAAAAAElFTkSuQmCC","orcid":"","institution":"Northwest Normal University","correspondingAuthor":true,"prefix":"","firstName":"Kunyi","middleName":"","lastName":"Zhu","suffix":""},{"id":630658982,"identity":"e821365d-3b90-47af-a645-ebf304586fa0","order_by":2,"name":"Tao Sun","email":"","orcid":"","institution":"Northwest Normal University","correspondingAuthor":false,"prefix":"","firstName":"Tao","middleName":"","lastName":"Sun","suffix":""}],"badges":[],"createdAt":"2026-04-16 08:54:56","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9435656/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9435656/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108977922,"identity":"36bc5bf9-ac0b-4d72-a14e-886957eb3d95","added_by":"auto","created_at":"2026-05-11 11:33:28","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1328745,"visible":true,"origin":"","legend":"","description":"","filename":"zky.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9435656/v1_covered_300c293c-f55a-40a8-a821-44981d504e99.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"SAD-ReID: Semantically-Anchored Dynamics for Unsupervised Vehicle Re-Identification","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":"journal-of-king-saud-university-computer-and-information-sciences","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Journal of King Saud University Computer and Information Sciences](https://link.springer.com/journal/44443)","snPcode":"44443","submissionUrl":"https://submission.springernature.com/new-submission/44443/3","title":"Journal of King Saud University Computer and Information Sciences","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Open","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Unsupervised Vehicle Re-ID, Vision-Language Models, Semantic Guidance, Reliability-Aware Learning","lastPublishedDoi":"10.21203/rs.3.rs-9435656/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9435656/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Unsupervised vehicle re-identification (Re-ID) is pivotal for scalable intelligent transportation systems but faces significant challenges from severe noise accumulation. Traditional clustering-based methods often suffer from error propagation during online training, as purely visual features are highly susceptible to intra-class viewpoint variations and inter-class similarities. To mitigate this fundamental limitation, we propose a novel Semantically-Anchored Dynamics (SAD-ReID) framework that exploits the viewpoint-invariant stability of text-induced semantic knowledge derived from Vision-Language Models. Specifically, we first introduce a Semantically-Guided Initialization strategy that fuses visual similarities with detailed textual descriptions generated automatically by Qwen-VL. This rectifies initial visual clusters to establish robust text-guided dual-prototype (visual and semantic) anchors. During the online learning phase, we propose a Reliability-Aware Dynamic Update (RADU) mechanism. By calculating a Cross-Modality Allegiance (CMA) score that measures the topological agreement between visual and textual spaces, RADU dynamically adjusts the memory update momentum. This efficiently accelerates learning from reliable samples while filtering out noisy pseudo-labels to prevent memory corruption. Furthermore, an Adaptive Granularity Attention Fusion (AGAF) module is designed to capture both global semantic attributes and fine-grained local discriminative details. Extensive experiments on the VeRi-776 and VehicleID benchmarks demonstrate the significant superiority of our approach over existing state-of-the-art methods, achieving an impressive Rank-1 accuracy of 90.0\\% and 43.2\\% mAP on VeRi-776. By enforcing text-visual semantic consistency throughout the evolutionary training process, SAD-ReID successfully prevents model drift and learns highly robust representations without any manual annotation.","manuscriptTitle":"SAD-ReID: Semantically-Anchored Dynamics for Unsupervised Vehicle Re-Identification","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-11 05:19:28","doi":"10.21203/rs.3.rs-9435656/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"203134093755415815378776629992911360902","date":"2026-04-27T23:35:41+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-27T14:12:51+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-17T12:22:58+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-17T12:22:33+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of King Saud University Computer and Information Sciences","date":"2026-04-16T08:45:29+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"journal-of-king-saud-university-computer-and-information-sciences","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Journal of King Saud University Computer and Information Sciences](https://link.springer.com/journal/44443)","snPcode":"44443","submissionUrl":"https://submission.springernature.com/new-submission/44443/3","title":"Journal of King Saud University Computer and Information Sciences","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Open","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"f7948cd2-ae25-40c0-a9ee-618b97541eff","owner":[],"postedDate":"May 11th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-11T05:19:28+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-11 05:19:28","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9435656","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9435656","identity":"rs-9435656","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}