Adaptive Feature Alignment and Enhancement for Precise Fine-Grained Visual Recognition

Adaptive Feature Alignment and Enhancement for Precise Fine-Grained Visual Recognition | 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 Adaptive Feature Alignment and Enhancement for Precise Fine-Grained Visual Recognition Qianhao Zhao, Jianlei Liu, Ke Zhang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8277343/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 6 You are reading this latest preprint version Abstract Fine-grained visual classification (FGVC) faces challenges in distinguishing subtle differences among visually similar categories. This paper introduces a novel adaptive part-aware feature alignment and enhancement network (PAAE) designed to effectively extract discriminative features. Our approach comprises a Progressive Part Mining Module for capturing discriminative features across different layers, an Adaptive Scale Displacement Alignment Module for addressing feature space misalignment, and a Dual-Path Feature Enhancement Module for highlighting foreground features. Experimental results on benchmark datasets demonstrate competitive performance, with an accuracy of 92.4% on the CUB-200-2011 dataset and 95.1% on the Stanford Dogs dataset, showcasing the efficacy of our proposed method. The source code will be made publicly available at https://github.com/XubaozZ/PAAE . Fine-grained visual classification Part mining Multi-scale feature alignment Attention Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 26 Feb, 2026 Reviewers agreed at journal 26 Feb, 2026 Reviewers invited by journal 19 Feb, 2026 Editor assigned by journal 05 Dec, 2025 Submission checks completed at journal 05 Dec, 2025 First submitted to journal 04 Dec, 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-8277343","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":593739195,"identity":"ae54292f-6ae8-45fc-abad-5f3b5060a9a4","order_by":0,"name":"Qianhao Zhao","email":"","orcid":"","institution":"Qufu Normal University","correspondingAuthor":false,"prefix":"","firstName":"Qianhao","middleName":"","lastName":"Zhao","suffix":""},{"id":593739196,"identity":"56e4b13f-5fb8-41b5-81bc-409ed1e922b4","order_by":1,"name":"Jianlei Liu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8UlEQVRIiWNgGAWjYBACxmYg8YBBQoaNgfkAQwVYLIEILQkMEjxsDGwJDGeI0QJTwwNEBsRpYW5nfvYgocKCh08i5+ONgzsOM/Cz5xgw/NyBz2Fs5gYJZ4AOk8jdbHHwzGEGyZ43Boy9Z/D6xUwisQ2sZZv0x7bDDAY3cgyYGdvwaWH/JpH4D6Ql55nEQaAWe8JaeIC2NIC1sIG1GEgQ1lImkXAMqIXnmbHFwbZ0HokzzwoO9uLRYth/fJvEh5o6Ofn25Ic3DrZZy/G3J2988BOflgYkjgQDOIIYGA7g1sDAII/MkcCnchSMglEwCkYuAACmkknv5ZSzTAAAAABJRU5ErkJggg==","orcid":"","institution":"Qufu Normal University","correspondingAuthor":true,"prefix":"","firstName":"Jianlei","middleName":"","lastName":"Liu","suffix":""},{"id":593739197,"identity":"d587a1a8-203d-47af-b771-265e2c7b6c03","order_by":2,"name":"Ke Zhang","email":"","orcid":"","institution":"Qufu Normal University","correspondingAuthor":false,"prefix":"","firstName":"Ke","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2025-12-04 09:23:30","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8277343/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8277343/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104397809,"identity":"86f8cdb0-17c3-4a18-ab36-62f3fda76628","added_by":"auto","created_at":"2026-03-11 11:56:46","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1384060,"visible":true,"origin":"","legend":"","description":"","filename":"PAAE.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8277343/v1_covered_5cec2fcc-a6d8-41e6-aed8-1b9f882b1a5d.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Adaptive Feature Alignment and Enhancement for Precise Fine-Grained Visual Recognition","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":"Fine-grained visual classification, Part mining, Multi-scale feature alignment, Attention","lastPublishedDoi":"10.21203/rs.3.rs-8277343/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8277343/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Fine-grained visual classification (FGVC) faces challenges in distinguishing subtle differences among visually similar categories. This paper introduces a novel adaptive part-aware feature alignment and enhancement network (PAAE) designed to effectively extract discriminative features. Our approach comprises a Progressive Part Mining Module for capturing discriminative features across different layers, an Adaptive Scale Displacement Alignment Module for addressing feature space misalignment, and a Dual-Path Feature Enhancement Module for highlighting foreground features. Experimental results on benchmark datasets demonstrate competitive performance, with an accuracy of 92.4% on the CUB-200-2011 dataset and 95.1% on the Stanford Dogs dataset, showcasing the efficacy of our proposed method. The source code will be made publicly available at https://github.com/XubaozZ/PAAE.","manuscriptTitle":"Adaptive Feature Alignment and Enhancement for Precise Fine-Grained Visual Recognition","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-23 08:37:32","doi":"10.21203/rs.3.rs-8277343/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-02-26T14:43:39+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"81357275531566603495668655971263188903","date":"2026-02-26T12:06:28+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-02-19T07:24:02+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-12-05T13:03:03+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-12-05T11:01:27+00:00","index":"","fulltext":""},{"type":"submitted","content":"The Visual Computer","date":"2025-12-04T09:18:17+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":"15423457-c330-433c-a706-0f063a9f9a76","owner":[],"postedDate":"February 23rd, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-02-23T08:37:32+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-23 08:37:32","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8277343","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8277343","identity":"rs-8277343","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}