Self-supervised learning method of image maskbased on enhanced chunk embedding andthreshold binarization

Self-supervised learning method of image maskbased on enhanced chunk embedding andthreshold binarization | 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 Self-supervised learning method of image maskbased on enhanced chunk embedding andthreshold binarization Yunxue Shao, Zhiyang Wang, Lingfeng Wang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4988369/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Self-supervised learning is popular for avoiding labeling large-scale datasets to reduce the cost, effectively improving the model's generalization and representation ability . Masking self-supervised learning is the hot spot of self-supervised learning nowadays, most of the existing masking methods are masking the regular chunks after data enhancement chunking, which is not the real sense of random masking, and at the same time, the above masking methods result in a poor local correlation between the chunks of the image. In this paper, we propose a new masking method for self-supervised learning, named TBMP, which masks the image after threshold binarisation before data enhancement, and enhances the chunked embedding between chunks while aggregating the input position information, effectively enhancing the local correlation between image chunks in the model, and solving the problem of mask shape region fixation in the current self-supervised learning. We use the DINO model as a benchmark for which we perform threshold binarisation masking as well as augmented chunk embedding. In this paper, we conduct linear evaluation experiments on several public datasets, and the results show that the TBMP method outperforms all existing mainstream models in self-supervised learning using masks. Self-supervised learning threshold binarization masking mechanisms chunked embedding Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted 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-4988369","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":350901172,"identity":"1165dc98-6408-4d1c-ad9c-1a14ddc37ad1","order_by":0,"name":"Yunxue Shao","email":"","orcid":"","institution":"Nanjing Tech University","correspondingAuthor":false,"prefix":"","firstName":"Yunxue","middleName":"","lastName":"Shao","suffix":""},{"id":350901173,"identity":"ea40c96b-43f6-4d03-bbf2-4325759774cb","order_by":1,"name":"Zhiyang Wang","email":"","orcid":"","institution":"Nanjing Tech University","correspondingAuthor":false,"prefix":"","firstName":"Zhiyang","middleName":"","lastName":"Wang","suffix":""},{"id":350901174,"identity":"a6e9dd93-5412-4ba2-8780-4b17fc8d185f","order_by":2,"name":"Lingfeng Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA20lEQVRIiWNgGAWjYBACPuYDIMqGgQ9EJRCjhY0NrCyNgY1ULYchWogCbGw8hp8Lfp3PY5PufcDwoIZBnr+B+dkDAlqMpWf23S5mkzluwJBwjMFwxgE2cwO8WuR7N0jz9txObJNIA/qFjYFxAwMPmwR+W3g3/+btOQfV8o/Bnhgt26R5fhyAaElsY0gkQgv/N2vehuTENpljDAcS+ySSZxxmM8OrhZ+NLfk2zx+7xH7pNsaHP77Z2Pa3Nz/DqwUMGNuABFDZATDJTFA9CPyBaBkFo2AUjIJRgBUAAL8wO4/5Na/jAAAAAElFTkSuQmCC","orcid":"","institution":"Binzhou Institute of Technology, Weiqiao-UCAS Science and Technology Park, Binzhou, Shandong Province, China;","correspondingAuthor":true,"prefix":"","firstName":"Lingfeng","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2024-08-28 05:44:21","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4988369/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4988369/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":67788316,"identity":"97e785e7-1f92-415d-88d1-7e7d27bd67bb","added_by":"auto","created_at":"2024-10-29 17:32:22","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3515899,"visible":true,"origin":"","legend":"","description":"","filename":"TBMP.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4988369/v1_covered_f6cab6f1-9f1c-47d9-a1bb-62edf103ba5d.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Self-supervised learning method of image maskbased on enhanced chunk embedding andthreshold binarization","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"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":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Self-supervised learning, threshold binarization, masking mechanisms, chunked embedding","lastPublishedDoi":"10.21203/rs.3.rs-4988369/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4988369/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Self-supervised learning is popular for avoiding labeling large-scale datasets to reduce the cost, effectively improving the model's generalization and representation ability . Masking self-supervised learning is the hot spot of self-supervised learning nowadays, most of the existing masking methods are masking the regular chunks after data enhancement chunking, which is not the real sense of random masking, and at the same time, the above masking methods result in a poor local correlation between the chunks of the image. In this paper, we propose a new masking method for self-supervised learning, named TBMP, which masks the image after threshold binarisation before data enhancement, and enhances the chunked embedding between chunks while aggregating the input position information, effectively enhancing the local correlation between image chunks in the model, and solving the problem of mask shape region fixation in the current self-supervised learning. We use the DINO model as a benchmark for which we perform threshold binarisation masking as well as augmented chunk embedding. In this paper, we conduct linear evaluation experiments on several public datasets, and the results show that the TBMP method outperforms all existing mainstream models in self-supervised learning using masks.","manuscriptTitle":"Self-supervised learning method of image maskbased on enhanced chunk embedding andthreshold binarization","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-10-01 05:59:51","doi":"10.21203/rs.3.rs-4988369/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"92b6dcac-eaf2-4b60-8423-167cbbcb9b0a","owner":[],"postedDate":"October 1st, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-10-29T17:24:10+00:00","versionOfRecord":[],"versionCreatedAt":"2024-10-01 05:59:51","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4988369","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4988369","identity":"rs-4988369","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}