Unified Pre-training with Pseudo Infrared Images for Visible-Infrared Person Re-identification

Unified Pre-training with Pseudo Infrared Images for Visible-Infrared 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 Unified Pre-training with Pseudo Infrared Images for Visible-Infrared Person Re-identification ZhiGang Liu, Yan Hu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4501669/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 3 You are reading this latest preprint version Abstract In the pre-training task of visible-infrared person re-identification(VI-ReID), two main challenges arise: i) Domain disparities. A significant domain gap exists between the ImageNet utilized in public pre-trained models and the specific person data in the VI-ReID task. ii) Insufficient sample. Due to the challenge of gathering cross-modal paired samples, there is currently a scarcity of large-scale datasets suitable for pretraininge. To address the aforementioned issues, we propose a new unified pre-training framework (UPPI). Firstly, we established a large-scale visible-pseudo infrared paired sample repository (UnitCP) based on the existing visible person dataset, encompassing nearly 170,000 sample pairs. Benefiting from this repository, not only are training samples significantly expanded, but pre-training on this foundation also effectively bridges the domain disparities. Simultaneously, to fully harness the potential of the repository, we devised an innovative feature fusion mechanism(CF 2) during pre-training. It leverages redundant features present in the paired images to steer the model towards cross-modal feature fusion. In addition, during fine-tuning, to adapt the model to datasets lacking paired images, we introduced a center contrast loss(C 2). This loss guides the model to prioritize cross-modal features with consistent identities. Extensive experimental results on two standard benchmarks (SYSU-MM01 and RegDB) demonstrate that the proposed UPPI performs favorably against state-of-the-art methods. Cross-Modality Retrieval Visible-Infrared Person Re-identification Pre-training Tasks Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editor assigned by journal 31 May, 2024 Submission checks completed at journal 31 May, 2024 First submitted to journal 30 May, 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-4501669","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":309159758,"identity":"9b15b431-28dc-4a41-a9dd-d2daded17a31","order_by":0,"name":"ZhiGang Liu","email":"","orcid":"","institution":"Northeast Petroleum University","correspondingAuthor":false,"prefix":"","firstName":"ZhiGang","middleName":"","lastName":"Liu","suffix":""},{"id":309159759,"identity":"d27d5643-89be-44d2-abdb-b92b01aaa1cc","order_by":1,"name":"Yan Hu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6klEQVRIiWNgGAWjYBACNvnHBx98+GHDw8/MfPBBQkUNYS18DGnJhjN70uQk29mSDR6cOUZYixxDjpo0D9thY4PzPGaSD1uYiXAYwxkGyRk8hxM3HOYxq0hsYGPgb+9OwK+FsfeAwQeL9MSZh9nKbiTukGGQOHN2A34tzHwJiTN4rBP7DjNvu5F4ho3BQCKXgBY2HoPDPGzMiQ2HGcwKEtuYidDCw2PYzMPmbCxwmMWMgTgtEmzJjOBAbmZLlkg4c4yHoF/kZzAf/wGOSv7DBz/+qKiR42/vxa8FA/CQpnwUjIJRMApGAVYAALF1SKplM7NkAAAAAElFTkSuQmCC","orcid":"","institution":"Northeast Petroleum University","correspondingAuthor":true,"prefix":"","firstName":"Yan","middleName":"","lastName":"Hu","suffix":""}],"badges":[],"createdAt":"2024-05-30 08:52:01","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4501669/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4501669/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":58305855,"identity":"f8ce4742-f238-4a58-8676-4638a8fe9391","added_by":"auto","created_at":"2024-06-13 18:18:05","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1425885,"visible":true,"origin":"","legend":"","description":"","filename":"UPPI.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4501669/v1_covered_74423c3b-9c96-40c3-8e6d-3fa44b3b5ca3.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Unified Pre-training with Pseudo Infrared Images for Visible-Infrared Person 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":"the-visual-computer","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"tvcj","sideBox":"Learn more about [The Visual Computer](http://link.springer.com/journal/371)","snPcode":"371","submissionUrl":"https://submission.nature.com/new-submission/371/3","title":"The Visual Computer","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":" Cross-Modality Retrieval, Visible-Infrared Person Re-identification, Pre-training Tasks","lastPublishedDoi":"10.21203/rs.3.rs-4501669/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4501669/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"In the pre-training task of visible-infrared person re-identification(VI-ReID), two main challenges arise: i) Domain disparities. A significant domain gap exists between the ImageNet utilized in public pre-trained models and the specific person data in the VI-ReID task. ii) Insufficient sample. Due to the challenge of gathering cross-modal paired samples, there is currently a scarcity of large-scale datasets suitable for pretraininge. To address the aforementioned issues, we propose a new unified pre-training framework (UPPI). Firstly, we established a large-scale visible-pseudo infrared paired sample repository (UnitCP) based on the existing visible person dataset, encompassing nearly 170,000 sample pairs. Benefiting from this repository, not only are training samples significantly expanded, but pre-training on this foundation also effectively bridges the domain disparities. Simultaneously, to fully harness the potential of the repository, we devised an innovative feature fusion mechanism(CF 2) during pre-training. It leverages redundant features present in the paired images to steer the model towards cross-modal feature fusion. In addition, during fine-tuning, to adapt the model to datasets lacking paired images, we introduced a center contrast loss(C 2). This loss guides the model to prioritize cross-modal features with consistent identities. Extensive experimental results on two standard benchmarks (SYSU-MM01 and RegDB) demonstrate that the proposed UPPI performs favorably against state-of-the-art methods.","manuscriptTitle":"Unified Pre-training with Pseudo Infrared Images for Visible-Infrared Person Re-identification","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-06-13 18:09:57","doi":"10.21203/rs.3.rs-4501669/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorAssigned","content":"","date":"2024-05-31T15:05:50+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-05-31T11:38:27+00:00","index":"","fulltext":""},{"type":"submitted","content":"The Visual Computer","date":"2024-05-30T08:50:31+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"the-visual-computer","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"tvcj","sideBox":"Learn more about [The Visual Computer](http://link.springer.com/journal/371)","snPcode":"371","submissionUrl":"https://submission.nature.com/new-submission/371/3","title":"The Visual Computer","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"6cd1acc2-84ff-49f4-9faf-1602cea83ffe","owner":[],"postedDate":"June 13th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2024-07-24T03:12:07+00:00","versionOfRecord":[],"versionCreatedAt":"2024-06-13 18:09:57","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4501669","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4501669","identity":"rs-4501669","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}