Visual-Textual Adversarial Learning for Person Re-Identification

Visual-Textual Adversarial Learning for Person 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Research Article Visual-Textual Adversarial Learning for Person Re-Identification Pengqi Yin This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5257618/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 16 Jan, 2025 Read the published version in Multimedia Systems → Version 1 posted 9 You are reading this latest preprint version Abstract Person Re-identification(ReID) aims to generate a discriminative description model to search the probe person from the gallery images.Previous methods infer the ReID model by constructing the metric learning between the visual space and the annotated label space. Moreover, the textual knowledge inferred by the visual-language model is introduced in CLIP-ReID to enhance the descriptive ability of the ReID model. However, the textual knowledge inferred from the pre-trained visual space has less discriminative ability on ReID tasks.To address the above issue, we propose a novel Visual-Textual Adversarial Learning(VTAL) for person ReID.The primary concept of VTAL is to construct an adversarial loop between the visual encoder and the text encoder, leveraging the progressive enhancement of one encoder to improve the performance of the other within this loop.Two types of prompts(Task-Independent prompt and Task-Related prompt) are deployed to maintain the generalization ability and discrimination ability of the generated textual-level identity embedding simultaneously.After that, the generated corresponding identity embeddings are treated as a textual-to-visual constraint to optimize the visual encoder.Extensive experiments on three benchmarks verify the effectiveness of the proposed method for person ReID.. Person Re-Identification Visual-Textual Adversarial Learning Prompt Tuning Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 16 Jan, 2025 Read the published version in Multimedia Systems → Version 1 posted Editorial decision: Revision requested 08 Dec, 2024 Reviews received at journal 04 Dec, 2024 Reviews received at journal 29 Nov, 2024 Reviewers agreed at journal 27 Nov, 2024 Reviewers agreed at journal 25 Nov, 2024 Reviewers invited by journal 25 Nov, 2024 Editor assigned by journal 25 Nov, 2024 Submission checks completed at journal 14 Oct, 2024 First submitted to journal 13 Oct, 2024 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-5257618","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":387561993,"identity":"ac9b7bb7-f7a4-4abd-ba14-71b7d6a25f13","order_by":0,"name":"Pengqi Yin","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+0lEQVRIiWNgGAWjYDACZijNxt7Y+OBDhQQpWngOHzaccYYYLXAgkZYmzdtGhEKD47zHHnzcUSvbx5BjIME7z0Kegf3wA4afO/BoOcyXbjjzzHHjNoYzBgaS2yQMG3jSDBh7z+DTwmMGdM+xxDbGHoMEw20SjA0MOQzMjHhcCNbyF6SFmcfgQOIcCfsG/jdEaGFsq0lsY2NLbDjYIJHYIEHAFsnDPOaGvW0HjNt4mA8zNhyTSG6TeGZwsBePFr7zZ8we/Gyrk50//2H77z81dbb9/MkPgSK4tSgcYGADUkALYCIg7gHcGhgY5BvAauoQWkbBKBgFo2AUoAMAm1FQ+ytAdJQAAAAASUVORK5CYII=","orcid":"","institution":"Institute of Automation，Chinese Academy of Sciences","correspondingAuthor":true,"prefix":"","firstName":"Pengqi","middleName":"","lastName":"Yin","suffix":""}],"badges":[],"createdAt":"2024-10-14 03:08:20","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5257618/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5257618/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00530-024-01648-7","type":"published","date":"2025-01-16T15:56:59+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":74284468,"identity":"0b7fcd05-22ee-4909-8722-62470beecf3b","added_by":"auto","created_at":"2025-01-20 16:06:34","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":593312,"visible":true,"origin":"","legend":"","description":"","filename":"mmsystem2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5257618/v1_covered_c6083014-103a-4627-b851-43add8ed648e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Visual-Textual Adversarial Learning for Person Re-Identification","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":"multimedia-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mmsj","sideBox":"Learn more about [Multimedia Systems](http://link.springer.com/journal/530)","snPcode":"530","submissionUrl":"https://submission.nature.com/new-submission/530/3","title":"Multimedia Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Person Re-Identification, Visual-Textual Adversarial Learning, Prompt Tuning","lastPublishedDoi":"10.21203/rs.3.rs-5257618/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5257618/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003ePerson Re-identification(ReID) aims to generate a discriminative description model to search the probe person from the gallery images.Previous methods infer the ReID model by constructing the metric learning between the visual space and the annotated label space. Moreover, the textual knowledge inferred by the visual-language model is introduced in CLIP-ReID to enhance the descriptive ability of the ReID model. However, the textual knowledge inferred from the pre-trained visual space has less discriminative ability on ReID tasks.To address the above issue, we propose a novel Visual-Textual Adversarial Learning(VTAL) for person ReID.The primary concept of VTAL is to construct an adversarial loop between the visual encoder and the text encoder, leveraging the progressive enhancement of one encoder to improve the performance of the other within this loop.Two types of prompts(Task-Independent prompt and Task-Related prompt) are deployed to maintain the generalization ability and discrimination ability of the generated textual-level identity embedding simultaneously.After that, the generated corresponding identity embeddings are treated as a textual-to-visual constraint to optimize the visual encoder.Extensive experiments on three benchmarks verify the effectiveness of the proposed method for person ReID..\u003c/p\u003e","manuscriptTitle":"Visual-Textual Adversarial Learning for Person Re-Identification","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-12-18 18:08:48","doi":"10.21203/rs.3.rs-5257618/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-12-08T07:50:44+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-12-04T13:02:50+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-11-30T02:58:41+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"144345433748335503925120962817924338584","date":"2024-11-27T11:11:46+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"274172460235105387595299475374181934941","date":"2024-11-25T14:10:26+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-11-25T13:01:57+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-11-25T12:51:13+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-10-14T08:16:51+00:00","index":"","fulltext":""},{"type":"submitted","content":"Multimedia Systems","date":"2024-10-14T03:06:56+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"multimedia-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mmsj","sideBox":"Learn more about [Multimedia Systems](http://link.springer.com/journal/530)","snPcode":"530","submissionUrl":"https://submission.nature.com/new-submission/530/3","title":"Multimedia Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"f3c7c16d-ca6d-4478-b3fb-99e80767d674","owner":[],"postedDate":"December 18th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-01-20T15:59:02+00:00","versionOfRecord":{"articleIdentity":"rs-5257618","link":"https://doi.org/10.1007/s00530-024-01648-7","journal":{"identity":"multimedia-systems","isVorOnly":false,"title":"Multimedia Systems"},"publishedOn":"2025-01-16 15:56:59","publishedOnDateReadable":"January 16th, 2025"},"versionCreatedAt":"2024-12-18 18:08:48","video":"","vorDoi":"10.1007/s00530-024-01648-7","vorDoiUrl":"https://doi.org/10.1007/s00530-024-01648-7","workflowStages":[]},"version":"v1","identity":"rs-5257618","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5257618","identity":"rs-5257618","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}