Label-Graph Guided Semantic Alignment for Multi-Class Remote Sensing Image Recognition

Label-Graph Guided Semantic Alignment for Multi-Class Remote Sensing Image 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 Label-Graph Guided Semantic Alignment for Multi-Class Remote Sensing Image Recognition KUN ZHOU, LIWEI ZHU, YI ZHANG, CUNCUN WEI This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9190415/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 4 You are reading this latest preprint version Abstract In multi-class remote sensing image classification, semantic confusion among similar classes often limits performance, as conventional one-hot labels cannot express inter-class relationships. To address this issue, we propose a Label-Graph-Guided Semantic Alignment method that leverages a data-driven label graph to enhance both the training supervision and the model predictions. Specifically, we construct a label graph from the confusion matrix to capture class similarities, and introduce two novel mechanisms: Graph-Soft at the supervision level and Graph-Logit at the prediction level. Graph-Soft utilizes the label graph to refine one-hot labels into soft label vectors. Meanwhile, Graph-Logit encourages the model's logits to respect label similarities, aligning the semantic space of predictions with that of labels. The proposed approach is lightweight and architecture-agnostic, introducing negligible computational overhead and requiring no additional annotations. Experiments on multiple remote sensing scene classification benchmarks (EuroSAT, MLRSNet and RESISC45) with different backbones (ResNet18, ResNet50) demonstrate consistent performance gains. Our method outperforms standard one-hot training across all tested datasets, improving classification accuracy, AUC, and F1-score. Notably, it achieves up to a 2-3% increase in accuracy on challenging benchmarks compared to the baseline. These results validate that incorporating label graph knowledge effectively reduces semantic confusion and enhances multi-class classification performance. The source code is publicly available at https://github.com/zhoukuniyc/GLSGLR/tree/master . Remote sensing image classification Label graph Semantic alignment Inter-class dependency Confusion-aware learning Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers invited by journal 28 Mar, 2026 Editor assigned by journal 24 Mar, 2026 Submission checks completed at journal 24 Mar, 2026 First submitted to journal 22 Mar, 2026 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-9190415","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":614983139,"identity":"1ea9b960-8206-4c90-8721-8f39e692fd15","order_by":0,"name":"KUN ZHOU","email":"","orcid":"","institution":"Zhejiang Business Technology Institute","correspondingAuthor":false,"prefix":"","firstName":"KUN","middleName":"","lastName":"ZHOU","suffix":""},{"id":614983140,"identity":"c3dd6c7b-b99a-4615-93ce-54176231d265","order_by":1,"name":"LIWEI ZHU","email":"","orcid":"","institution":"Zhejiang Shangong Intelligent Technology","correspondingAuthor":false,"prefix":"","firstName":"LIWEI","middleName":"","lastName":"ZHU","suffix":""},{"id":614983141,"identity":"e58e8152-316b-41c0-8ece-4adfb9b43f14","order_by":2,"name":"YI ZHANG","email":"","orcid":"","institution":"Zhejiang Business Technology Institute","correspondingAuthor":false,"prefix":"","firstName":"YI","middleName":"","lastName":"ZHANG","suffix":""},{"id":614983142,"identity":"3e2492e8-a5ea-42f4-b52f-873c349f7ba2","order_by":3,"name":"CUNCUN WEI","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAt0lEQVRIiWNgGAWjYFACxgYIzd7Y+PADaVp4DjcbS5Bmm0R6mwAPMQoNjjc3fubdYZe4XfJhG4MEg52cbgMhLWcONkvznklO3Dk7se1BAUOysdkBAlrMbiS2MfO2HUjccDux3UCC4UDiNoJa7j+Earl5sE2ChygtNxihWoAM4rTYn0lslpzblmy8AcgwljAgwi+S7ccffnjbZie74fjxhw8/VNjJEdSCBgxIUz4KRsEoGAWjAAcAAL/1Rj4T6qmsAAAAAElFTkSuQmCC","orcid":"","institution":"Zhejiang Business Technology Institute","correspondingAuthor":true,"prefix":"","firstName":"CUNCUN","middleName":"","lastName":"WEI","suffix":""}],"badges":[],"createdAt":"2026-03-22 10:08:16","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9190415/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9190415/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106414809,"identity":"7f9bcfae-1a1c-4176-9507-ef11a7c1cd9c","added_by":"auto","created_at":"2026-04-08 10:24:58","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1393976,"visible":true,"origin":"","legend":"","description":"","filename":"latex1.2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9190415/v1_covered_c09975ad-9525-43be-abdf-8975e76e354e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Label-Graph Guided Semantic Alignment for Multi-Class Remote Sensing Image 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":"signal-image-and-video-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"sivp","sideBox":"Learn more about [Signal, Image and Video Processing](http://link.springer.com/journal/11760)","snPcode":"11760","submissionUrl":"https://submission.nature.com/new-submission/11760/3","title":"Signal, Image and Video Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Remote sensing image classification, Label graph, Semantic alignment, Inter-class dependency, Confusion-aware learning","lastPublishedDoi":"10.21203/rs.3.rs-9190415/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9190415/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e In multi-class remote sensing image classification, semantic confusion among similar classes often limits performance, as conventional one-hot labels cannot express inter-class relationships. To address this issue, we propose a Label-Graph-Guided Semantic Alignment method that leverages a data-driven label graph to enhance both the training supervision and the model predictions. Specifically, we construct a label graph from the confusion matrix to capture class similarities, and introduce two novel mechanisms: Graph-Soft at the supervision level and Graph-Logit at the prediction level. Graph-Soft utilizes the label graph to refine one-hot labels into soft label vectors. Meanwhile, Graph-Logit encourages the model's logits to respect label similarities, aligning the semantic space of predictions with that of labels. The proposed approach is lightweight and architecture-agnostic, introducing negligible computational overhead and requiring no additional annotations. Experiments on multiple remote sensing scene classification benchmarks (EuroSAT, MLRSNet and RESISC45) with different backbones (ResNet18, ResNet50) demonstrate consistent performance gains. Our method outperforms standard one-hot training across all tested datasets, improving classification accuracy, AUC, and F1-score. Notably, it achieves up to a 2-3% increase in accuracy on challenging benchmarks compared to the baseline. These results validate that incorporating label graph knowledge effectively reduces semantic confusion and enhances multi-class classification performance. The source code is publicly available at \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://github.com/zhoukuniyc/GLSGLR/tree/master\u003c/span\u003e\u003cspan address=\"https://github.com/zhoukuniyc/GLSGLR/tree/master\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/p\u003e","manuscriptTitle":"Label-Graph Guided Semantic Alignment for Multi-Class Remote Sensing Image Recognition","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-02 02:31:13","doi":"10.21203/rs.3.rs-9190415/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewersInvited","content":"","date":"2026-03-29T02:20:40+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-03-25T02:10:42+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-25T02:09:57+00:00","index":"","fulltext":""},{"type":"submitted","content":"Signal, Image and Video Processing","date":"2026-03-22T09:56:16+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"signal-image-and-video-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"sivp","sideBox":"Learn more about [Signal, Image and Video Processing](http://link.springer.com/journal/11760)","snPcode":"11760","submissionUrl":"https://submission.nature.com/new-submission/11760/3","title":"Signal, Image and Video Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"f3c39879-f420-48ba-a783-1668654b839c","owner":[],"postedDate":"April 2nd, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-04-02T02:31:13+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-02 02:31:13","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9190415","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9190415","identity":"rs-9190415","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}