Calibrating Feature Representations for Few-shot Image Recognition via Vicinal Mixup

Calibrating Feature Representations for Few-shot Image Recognition via Vicinal Mixup | 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 Calibrating Feature Representations for Few-shot Image Recognition via Vicinal Mixup Wuyuan Ye, Zhengdong Luo, Mengcheng Chen This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6973369/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 27 Oct, 2025 Read the published version in Multimedia Systems → Version 1 posted 9 You are reading this latest preprint version Abstract The goal of few-shot image recognition (FSIR) is to identify novel categories with a small number of annotated samples by exploiting transferable knowledge from training data (base categories). Metric-based methods use these base categories to learn a feature embedding network, and then fix the embedding network to identify novel categories. However, due to discrepancies between concepts of novel and base categories, the fixed embedding network produces less distinguishable features for novel categories. To this end, we propose a vicinal Mixup method to calibrate feature representations of novel categories by fine-tuning the embedding network. Unlike traditional Mixup, which involves all samples in standard image recognition, the proposed method employs Mixup between novel and vicinal base samples to refine the embedding network. The proposed method generates plentiful mixed representations that enhance the feature learning of novel categories, resulting in better generalization ability. Moreover, a better initialization of a novel classifier than a random one is achieved with the class prototype, and it can be used for both inductive FSIR and transductive FSIR. Experimental results on four standard FSIR datasets and cross-domain FSIR datasets demonstrate the effectiveness of the proposed method. Few-shot Image Recognition Mixup Vicinal Learning Fine-tuning Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 27 Oct, 2025 Read the published version in Multimedia Systems → Version 1 posted Editorial decision: Revision requested 21 Aug, 2025 Reviews received at journal 20 Aug, 2025 Reviews received at journal 20 Aug, 2025 Reviewers agreed at journal 09 Aug, 2025 Reviewers agreed at journal 31 Jul, 2025 Reviewers invited by journal 30 Jul, 2025 Editor assigned by journal 30 Jul, 2025 Submission checks completed at journal 02 Jul, 2025 First submitted to journal 25 Jun, 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-6973369","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":494039736,"identity":"0cbf12ac-8bad-469c-863c-18c810545492","order_by":0,"name":"Wuyuan Ye","email":"","orcid":"","institution":"East China Jiaotong University","correspondingAuthor":false,"prefix":"","firstName":"Wuyuan","middleName":"","lastName":"Ye","suffix":""},{"id":494039738,"identity":"630c7822-e50a-4623-b1d2-8939731545a0","order_by":1,"name":"Zhengdong Luo","email":"data:image/png;base64,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","orcid":"","institution":"Chinese Academy of Sciences","correspondingAuthor":true,"prefix":"","firstName":"Zhengdong","middleName":"","lastName":"Luo","suffix":""},{"id":494039740,"identity":"3942cc7a-18ce-40dd-a687-2f26d063786c","order_by":2,"name":"Mengcheng Chen","email":"","orcid":"","institution":"East China Jiaotong University","correspondingAuthor":false,"prefix":"","firstName":"Mengcheng","middleName":"","lastName":"Chen","suffix":""}],"badges":[],"createdAt":"2025-06-25 10:08:17","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6973369/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6973369/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00530-025-02045-4","type":"published","date":"2025-10-27T15:58:01+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":95040007,"identity":"3c7fdf97-ccaf-4a70-9f9b-7c842e7e9f11","added_by":"auto","created_at":"2025-11-03 16:07:20","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2717792,"visible":true,"origin":"","legend":"","description":"","filename":"MultimediaSystems.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6973369/v1_covered_8dc36867-65b8-4220-bce4-6a9184f3b86e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Calibrating Feature Representations for Few-shot Image Recognition via Vicinal Mixup","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":"Few-shot Image Recognition, Mixup, Vicinal Learning, Fine-tuning","lastPublishedDoi":"10.21203/rs.3.rs-6973369/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6973369/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The goal of few-shot image recognition (FSIR) is to identify novel categories with a small number of annotated samples by exploiting transferable knowledge from training data (base categories). Metric-based methods use these base categories to learn a feature embedding network, and then fix the embedding network to identify novel categories. However, due to discrepancies between concepts of novel and base categories, the fixed embedding network produces less distinguishable features for novel categories. To this end, we propose a vicinal Mixup method to calibrate feature representations of novel categories by fine-tuning the embedding network. Unlike traditional Mixup, which involves all samples in standard image recognition, the proposed method employs Mixup between novel and vicinal base samples to refine the embedding network. The proposed method generates plentiful mixed representations that enhance the feature learning of novel categories, resulting in better generalization ability.\nMoreover, a better initialization of a novel classifier than a random one is achieved with the class prototype, and it can be used for both inductive FSIR and transductive FSIR. Experimental results on four standard FSIR datasets and cross-domain FSIR datasets demonstrate the effectiveness of the proposed method.","manuscriptTitle":"Calibrating Feature Representations for Few-shot Image Recognition via Vicinal Mixup","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-05 12:38:03","doi":"10.21203/rs.3.rs-6973369/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-08-21T04:00:01+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-08-20T06:06:25+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-08-20T04:59:33+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"180702641310739918726197661541511069295","date":"2025-08-09T06:14:18+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"26269651685740108825168805815499286628","date":"2025-08-01T03:21:22+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-07-31T02:03:30+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-07-30T11:02:28+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-07-02T11:27:28+00:00","index":"","fulltext":""},{"type":"submitted","content":"Multimedia Systems","date":"2025-06-25T09:57:35+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":"edef25cc-19c1-4f61-a2f5-c246cb3b4638","owner":[],"postedDate":"August 5th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-11-03T16:02:08+00:00","versionOfRecord":{"articleIdentity":"rs-6973369","link":"https://doi.org/10.1007/s00530-025-02045-4","journal":{"identity":"multimedia-systems","isVorOnly":false,"title":"Multimedia Systems"},"publishedOn":"2025-10-27 15:58:01","publishedOnDateReadable":"October 27th, 2025"},"versionCreatedAt":"2025-08-05 12:38:03","video":"","vorDoi":"10.1007/s00530-025-02045-4","vorDoiUrl":"https://doi.org/10.1007/s00530-025-02045-4","workflowStages":[]},"version":"v1","identity":"rs-6973369","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6973369","identity":"rs-6973369","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}