Label Enhancement Hashing Induced by Class Prototypes for Domain Adaptive Retrieval

Label Enhancement Hashing Induced by Class Prototypes for Domain Adaptive Retrieval | 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 Label Enhancement Hashing Induced by Class Prototypes for Domain Adaptive Retrieval Chuwei Cheng, Yu Chen, Tianle Hu, Qiyu Deng, Sixian Chan, Xiaozhao Fang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6151321/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 10 Oct, 2025 Read the published version in Multimedia Systems → Version 1 posted 12 You are reading this latest preprint version Abstract Domain adaptive retrieval (DAR) aims to perform effective cross-domain retrieval by transferring knowledge from the source domain to the target domain and reducing domain distribution discrepancy. However, the target domain often lacks annotations, and using pseudo-labels generated for target data may reduce retrieval accuracy due to their inaccuracy. Additionally, although features from the same class may differ across domains, they share global invariant information crucial for identifying samples in different domains. To address these challenges, this paper proposes a novel DAR method, Label Enhancement Hashing induced by Class Prototypes (LEHC). The approach first projects source and target domain features into a common subspace to reduce feature redundancy and domain discrepancy. Then, a label enhancement strategy is applied to convert discrete labels into continuous values, enriching semantic information. Orthogonal class prototypes in the common subspace capture global invariant information and induce relationships between enhanced labels and sample features. Finally, asymmetric similarity preserving is proposed, which retains both the pairwise similarity of the samples and the enhanced label information into hash codes. Experimental results on various benchmark datasets validate the effectiveness of LEHC, showing its superior performance in domain adaptive retrieval tasks. Domain Adaptive Retrieval Domain Adaptation Transfer Learning Label Enhancement Hashing Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 10 Oct, 2025 Read the published version in Multimedia Systems → Version 1 posted Editorial decision: Revision requested 25 May, 2025 Reviews received at journal 23 May, 2025 Reviews received at journal 07 May, 2025 Reviewers agreed at journal 23 Apr, 2025 Reviewers agreed at journal 19 Apr, 2025 Reviewers agreed at journal 17 Apr, 2025 Reviewers agreed at journal 16 Apr, 2025 Reviewers agreed at journal 16 Apr, 2025 Reviewers invited by journal 16 Apr, 2025 Editor assigned by journal 25 Mar, 2025 Submission checks completed at journal 05 Mar, 2025 First submitted to journal 04 Mar, 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-6151321","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":424320776,"identity":"d5c7f128-9b59-4d83-bcb6-3a6567036840","order_by":0,"name":"Chuwei Cheng","email":"","orcid":"","institution":"Guangdong University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Chuwei","middleName":"","lastName":"Cheng","suffix":""},{"id":424320777,"identity":"54fb1413-5d3f-4861-b87a-ae98b217b8a4","order_by":1,"name":"Yu Chen","email":"","orcid":"","institution":"Guangdong University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Yu","middleName":"","lastName":"Chen","suffix":""},{"id":424320778,"identity":"0e144a82-3898-4d01-86a2-d024baf469b3","order_by":2,"name":"Tianle Hu","email":"","orcid":"","institution":"Guangdong University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Tianle","middleName":"","lastName":"Hu","suffix":""},{"id":424320779,"identity":"0fdc45db-2423-49fa-acc0-cf93db9a56de","order_by":3,"name":"Qiyu Deng","email":"","orcid":"","institution":"Guangdong University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Qiyu","middleName":"","lastName":"Deng","suffix":""},{"id":424320781,"identity":"ae74415d-d2a4-4223-ae39-a89db06cc5b6","order_by":4,"name":"Sixian Chan","email":"","orcid":"","institution":"Zhejiang University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Sixian","middleName":"","lastName":"Chan","suffix":""},{"id":424320783,"identity":"272d30f0-78a5-4acb-8fd6-ff99e424b113","order_by":5,"name":"Xiaozhao Fang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3klEQVRIiWNgGAWjYFACHoYPIJKfvfnAgQ8VxGlhnAEkZSR7jiUenHGGBC02BjNyjA/zthChweD82YMNP3fU8hjwnPlwgLeBQZ5f7AB+LZIN5xIbe88c5zFn791wQHIHg+HM2Qn4tfAz9pg/4G07xmPZc3bDAcMzDAkGtwloYWPmMWz8C9RicCPnwYHENiK08LPxGDbzttWAtDAcOEiMFskeoBbZtgM8wEA2ONhwRoKwXwzOnzFsfNtWZw+Mysef/1TYyPNLE9ACBYdhDAmilINAHdEqR8EoGAWjYAQCADv5S8+zDCHwAAAAAElFTkSuQmCC","orcid":"","institution":"Guangdong University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Xiaozhao","middleName":"","lastName":"Fang","suffix":""}],"badges":[],"createdAt":"2025-03-04 06:23:21","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6151321/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6151321/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00530-025-02004-z","type":"published","date":"2025-10-10T15:57:12+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":93421227,"identity":"34f92efe-1e3d-40bf-afb8-78e6b2ec6205","added_by":"auto","created_at":"2025-10-13 16:10:51","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3801156,"visible":true,"origin":"","legend":"","description":"","filename":"LEHC.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6151321/v1_covered_a704b6ef-7945-4534-b9a4-0f06efabe467.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":" Label Enhancement Hashing Induced by Class Prototypes for Domain Adaptive\n\tRetrieval","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":"Domain Adaptive Retrieval, Domain Adaptation, Transfer Learning, Label Enhancement, Hashing","lastPublishedDoi":"10.21203/rs.3.rs-6151321/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6151321/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\n\nDomain adaptive retrieval (DAR) aims to perform effective cross-domain retrieval by transferring knowledge from the source domain to the target domain and reducing domain distribution discrepancy. However, the target domain often lacks annotations, and using pseudo-labels generated for target data may reduce retrieval accuracy due to their inaccuracy. Additionally, although features from the same class may differ across domains, they share global invariant information crucial for identifying samples in different domains. To address these challenges, this paper proposes a novel DAR method, Label Enhancement Hashing induced by Class Prototypes (LEHC). The approach first projects source and target domain features into a common subspace to reduce feature redundancy and domain discrepancy. Then, a label enhancement strategy is applied to convert discrete labels into continuous values, enriching semantic information. Orthogonal class prototypes in the common subspace capture global invariant information and induce relationships between enhanced labels and sample features. Finally, asymmetric similarity preserving is proposed, which retains both the pairwise similarity of the samples and the enhanced label information into hash codes. Experimental results on various benchmark datasets validate the effectiveness of LEHC, showing its superior performance in domain adaptive retrieval tasks.","manuscriptTitle":"Label Enhancement Hashing Induced by Class Prototypes for Domain Adaptive\nRetrieval","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-03-07 02:39:02","doi":"10.21203/rs.3.rs-6151321/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-05-25T06:36:15+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-23T14:39:18+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-07T15:59:40+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"326905615327984856464386118285984192995","date":"2025-04-23T06:23:53+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"154454367016388703492901401271676938763","date":"2025-04-19T05:37:24+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"94848377078747884916639207375895194035","date":"2025-04-17T08:29:41+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"148530929859658740392647587989651250874","date":"2025-04-16T16:41:07+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"307408530568760116988983920180376919883","date":"2025-04-16T15:18:51+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-04-16T13:44:28+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-03-26T02:31:36+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-03-05T06:30:07+00:00","index":"","fulltext":""},{"type":"submitted","content":"Multimedia Systems","date":"2025-03-04T06:16:27+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":"25069d7b-078c-41d1-8afd-0318660991f2","owner":[],"postedDate":"March 7th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-10-13T16:09:35+00:00","versionOfRecord":{"articleIdentity":"rs-6151321","link":"https://doi.org/10.1007/s00530-025-02004-z","journal":{"identity":"multimedia-systems","isVorOnly":false,"title":"Multimedia Systems"},"publishedOn":"2025-10-10 15:57:12","publishedOnDateReadable":"October 10th, 2025"},"versionCreatedAt":"2025-03-07 02:39:02","video":"","vorDoi":"10.1007/s00530-025-02004-z","vorDoiUrl":"https://doi.org/10.1007/s00530-025-02004-z","workflowStages":[]},"version":"v1","identity":"rs-6151321","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6151321","identity":"rs-6151321","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}