A Contrastive Learning Algorithm Based on Bayesian Random Semantic Feature Augmentation

A Contrastive Learning Algorithm Based on Bayesian Random Semantic Feature Augmentation | 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 A Contrastive Learning Algorithm Based on Bayesian Random Semantic Feature Augmentation Xiaofang Gao, Xianlei Meng This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7441449/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 The Simple Contrastive Learning (SimCLR) algorithm is a self-supervised method that projects high-dimensional features into a low-dimensional space to enhance the similarity between positive samples and the difference between negative samples. However, this projection may cause the loss of feature information, significantly impacting the performance of downstream tasks. Therefore, we propose A Bayesian Random Semantic Data Augmentation Algorithm (SimKFA), an improved contrastive learning algorithm. A learnable linear transformation layer, KLP, replaces the multilayer perceptron (MLP) to preserve feature information. A feature enhancement module (BFAB), which combines Bayesian inference and frequency-domain feature analysis, is proposed. This module adaptively captures key information, maintains the continuity of the information flow, and reduces feature loss during deep learning. The experimental results show that the proposed algorithm prevents loss of feature information caused by the projection head and achieves excellent performance on multiple benchmark datasets. Contrastive learning Bayesian inference Feature enhancement Frequency domain feature fusion 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-7441449","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":515089353,"identity":"bce552fb-54c7-4f1d-82a0-587f360f2b3f","order_by":0,"name":"Xiaofang Gao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAyElEQVRIiWNgGAWjYFACxmdAwgbC5iFOC7MZwwGGNNK1HCZBi3xEMtvjjzvO2xvcSGB88LaNQd6ckBbDM4fZDQ6euZ04c0YCs+HcNgbDnQ2EtLT3H5M42HY7gV8igU2at40hweAAIS3NzGxALefs2SQS2H8TpUWevRmk5QBjP9AWZqK0GPAcZpM4eyY5cWbPw2bJOeckDDcQtGVGMptE5Q47e4PjyQc/vCmzkSdsC0gBYwMDjJQgoB5kSwNcyygYBaNgFIwCHAAARTs+iL71X+wAAAAASUVORK5CYII=","orcid":"","institution":"Shanxi University","correspondingAuthor":true,"prefix":"","firstName":"Xiaofang","middleName":"","lastName":"Gao","suffix":""},{"id":515089354,"identity":"a10efa09-0df5-49b2-ac8c-a6cbe5c75279","order_by":1,"name":"Xianlei Meng","email":"","orcid":"","institution":"Shanxi University","correspondingAuthor":false,"prefix":"","firstName":"Xianlei","middleName":"","lastName":"Meng","suffix":""}],"badges":[],"createdAt":"2025-08-23 13:08:02","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7441449/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7441449/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":91817460,"identity":"292a697f-7a33-4fe9-9ac6-334d9e9d16f1","added_by":"auto","created_at":"2025-09-22 06:56:36","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":437848,"visible":true,"origin":"","legend":"","description":"","filename":"ImageNet100top201.png","url":"https://assets-eu.researchsquare.com/files/rs-7441449/v1/a832e861216ef8057396428a.png"},{"id":91817208,"identity":"a0931194-1042-4a6a-8b44-5a10043f88d8","added_by":"auto","created_at":"2025-09-22 06:54:11","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":39687,"visible":true,"origin":"","legend":"","description":"","filename":"KLP.png","url":"https://assets-eu.researchsquare.com/files/rs-7441449/v1/82db33b7fc1bbed3decdf7b1.png"},{"id":91817295,"identity":"95658a8e-0d4e-41bd-bf15-2d5df669c5c2","added_by":"auto","created_at":"2025-09-22 06:54:57","extension":"eps","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2890,"visible":true,"origin":"","legend":"","description":"","filename":"empty.eps","url":"https://assets-eu.researchsquare.com/files/rs-7441449/v1/0d47924e80e9ba250e67bffd.eps"},{"id":91817299,"identity":"8ebb58bf-5d92-49b3-858a-b86ee1344e42","added_by":"auto","created_at":"2025-09-22 06:55:04","extension":"pdf","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3100,"visible":true,"origin":"","legend":"","description":"","filename":"figepsconvertedto.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7441449/v1/ed8c27ce470f49a7fa2797be.pdf"},{"id":91817204,"identity":"8231addd-5831-4a52-9e98-de51d933b998","added_by":"auto","created_at":"2025-09-22 06:54:04","extension":"bst","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":151345,"visible":true,"origin":"","legend":"","description":"","filename":"snapacite.bst","url":"https://assets-eu.researchsquare.com/files/rs-7441449/v1/a171d26265a2bb107a847981.bst"},{"id":91816688,"identity":"0e93f2ff-a26c-4597-b0d2-0c984ee10826","added_by":"auto","created_at":"2025-09-22 06:52:35","extension":"blg","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2374,"visible":true,"origin":"","legend":"","description":"","filename":"snarticle.blg","url":"https://assets-eu.researchsquare.com/files/rs-7441449/v1/d84a088c16efc6da4201b5b7.blg"},{"id":91817057,"identity":"032af8a6-f1ec-4466-b335-b9dfedc9fc92","added_by":"auto","created_at":"2025-09-22 06:53:25","extension":"bst","order_by":29,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64164,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysnum.bst","url":"https://assets-eu.researchsquare.com/files/rs-7441449/v1/514a0ed3706b02af6b1cca67.bst"},{"id":98428230,"identity":"2e164fa1-bace-4b18-9f10-da0e277482b5","added_by":"auto","created_at":"2025-12-17 16:41:50","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3331545,"visible":true,"origin":"","legend":"","description":"","filename":"Snarticle1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7441449/v1_covered_5bc06ffd-6f4c-4863-9ff6-a8e46ff6837f.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Contrastive Learning Algorithm Based on Bayesian Random Semantic Feature Augmentation","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":"Contrastive learning, Bayesian inference, Feature enhancement, Frequency domain feature fusion","lastPublishedDoi":"10.21203/rs.3.rs-7441449/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7441449/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe Simple Contrastive Learning (SimCLR) algorithm is a self-supervised method that projects high-dimensional features into a low-dimensional space to enhance the similarity between positive samples and the difference between negative samples. However, this projection may cause the loss of feature information, significantly impacting the performance of downstream tasks. Therefore, we propose A Bayesian Random Semantic Data Augmentation Algorithm (SimKFA), an improved contrastive learning algorithm. A learnable linear transformation layer, KLP, replaces the multilayer perceptron (MLP) to preserve feature information. A feature enhancement module (BFAB), which combines Bayesian inference and frequency-domain feature analysis, is proposed. This module adaptively captures key information, maintains the continuity of the information flow, and reduces feature loss during deep learning. The experimental results show that the proposed algorithm prevents loss of feature information caused by the projection head and achieves excellent performance on multiple benchmark datasets.\u003c/p\u003e","manuscriptTitle":"A Contrastive Learning Algorithm Based on Bayesian Random Semantic Feature Augmentation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-19 04:55:47","doi":"10.21203/rs.3.rs-7441449/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":"c72351e5-c439-44d4-96e3-945c0c5faad4","owner":[],"postedDate":"September 19th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-12-12T16:38:57+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-19 04:55:47","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7441449","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7441449","identity":"rs-7441449","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}