MSA2T-Net: A Multiscale Attention Augmented Transformer Network for Hyperspectral Image Classification

MSA2T-Net: A Multiscale Attention Augmented Transformer Network for Hyperspectral Image Classification | 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 MSA 2 T-Net: A Multiscale Attention Augmented Transformer Network for Hyperspectral Image Classification Dekai Li, Uzair Aslam Bhatti, Muhammad Asif, Siling Feng, Yu Zhang, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6773180/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 Hyperspectral image classification is crucial in remote sensing but faces significant challenges, including long-range dependence in spatial-spectral information and the difficulty of effectively fusing spectral and spatial features. To address these issues, we propose a novel classification framework, Multiscale Attention Augmented Transformer Network (MSA 2 T-Net). The framework integrates three key modules: Dynamic Spatial Attention Unit (DSAU), Multi-Kernel Fusion Attention (MKFA), and Cross-Attention Swin Transformer (CASTB). These modules enhance feature representation, efficiently extract multi-scale features, and improve the integration of spatial and spectral information, which leads to improved classification consistency and robustness. Experimental results on four publicly available hyperspectral datasets (Pavia, Houston2013, PaviaU, and Salinas) demonstrate that MSA 2 T-Net outperforms state-of-the-art methods in overall accuracy, average accuracy, and Kappa coefficient. Ablation studies further confirm the effectiveness of each module. The proposed method offers a balanced solution for HSIC, achieving both high performance and low complexity. hyperspectral image Swin Transformer multiscale attention 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-6773180","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":485086090,"identity":"b521f27f-f992-4777-a692-7677bf86e628","order_by":0,"name":"Dekai Li","email":"","orcid":"","institution":"Hainan University","correspondingAuthor":false,"prefix":"","firstName":"Dekai","middleName":"","lastName":"Li","suffix":""},{"id":485086091,"identity":"51125c82-cd7d-4b9f-8f5a-2373633a3b94","order_by":1,"name":"Uzair Aslam Bhatti","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA2UlEQVRIiWNgGAWjYJCCAwwVBxjYoBzGBuK0nCFVCwNj2wEEm6AWg/OHHx6unHdHnk+6+dljHgYb2Q0HmJ89wKvlwDGDg2e3PTNskzlmbszDkGa84QCbuQFeLQcbDA42bjvM2CaRYCbNw3A4ccMBHjYJvFoOs3842DjnsH2bRPo3oJb/RGg5xgO0peFwYptEDsiWA4S1SJ7hKTjYcOxwMlBLmeQcg2TjmYfZzPBq4Tt/fPPHhprDtvNnpG+TeFNhJ9t3vPkZXi3o7gRiZhLUj4JRMApGwSjADgDnQEyCnB9KbgAAAABJRU5ErkJggg==","orcid":"","institution":"Hainan University","correspondingAuthor":true,"prefix":"","firstName":"Uzair","middleName":"Aslam","lastName":"Bhatti","suffix":""},{"id":485086092,"identity":"3043778f-8ada-456a-881e-d337b67bb760","order_by":2,"name":"Muhammad Asif","email":"","orcid":"","institution":"Hunan University of Science and Engineering","correspondingAuthor":false,"prefix":"","firstName":"Muhammad","middleName":"","lastName":"Asif","suffix":""},{"id":485086093,"identity":"9a5b76d8-9086-42bd-ba89-cbdb25f575c8","order_by":3,"name":"Siling Feng","email":"","orcid":"","institution":"Hainan University","correspondingAuthor":false,"prefix":"","firstName":"Siling","middleName":"","lastName":"Feng","suffix":""},{"id":485086094,"identity":"58ae0854-3d7f-43fd-9b50-cfc0cbafd825","order_by":4,"name":"Yu Zhang","email":"","orcid":"","institution":"Hainan University","correspondingAuthor":false,"prefix":"","firstName":"Yu","middleName":"","lastName":"Zhang","suffix":""},{"id":485086095,"identity":"ec8fe8f9-3c64-4f7f-bcb7-acb35c442a1e","order_by":5,"name":"Songpeng Gong","email":"","orcid":"","institution":"Hainan University","correspondingAuthor":false,"prefix":"","firstName":"Songpeng","middleName":"","lastName":"Gong","suffix":""}],"badges":[],"createdAt":"2025-05-29 06:08:20","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6773180/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6773180/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":90759272,"identity":"826a0df2-9fae-4f65-8ae5-98338fe9a978","added_by":"auto","created_at":"2025-09-07 14:46:59","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1915081,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6773180/v1_covered_398129cc-3c10-462b-b148-32119cff093c.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eMSA\u003c/strong\u003e\u003csup\u003e\u003cstrong\u003e2\u003c/strong\u003e\u003c/sup\u003e\u003cstrong\u003eT-Net: A Multiscale Attention Augmented Transformer Network for Hyperspectral Image Classification\u003c/strong\u003e\u003c/p\u003e","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":"hyperspectral image, Swin Transformer, multiscale attention, feature fusion","lastPublishedDoi":"10.21203/rs.3.rs-6773180/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6773180/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eHyperspectral image classification is crucial in remote sensing but faces significant challenges, including long-range dependence in spatial-spectral information and the difficulty of effectively fusing spectral and spatial features. To address these issues, we propose a novel classification framework, Multiscale Attention Augmented Transformer Network (MSA\u003csup\u003e2\u003c/sup\u003eT-Net). The framework integrates three key modules: Dynamic Spatial Attention Unit (DSAU), Multi-Kernel Fusion Attention (MKFA), and Cross-Attention Swin Transformer (CASTB). These modules enhance feature representation, efficiently extract multi-scale features, and improve the integration of spatial and spectral information, which leads to improved classification consistency and robustness. Experimental results on four publicly available hyperspectral datasets (Pavia, Houston2013, PaviaU, and Salinas) demonstrate that MSA\u003csup\u003e2\u003c/sup\u003eT-Net outperforms state-of-the-art methods in overall accuracy, average accuracy, and Kappa coefficient. Ablation studies further confirm the effectiveness of each module. The proposed method offers a balanced solution for HSIC, achieving both high performance and low complexity.\u003c/p\u003e","manuscriptTitle":"MSA2T-Net: A Multiscale Attention Augmented Transformer Network for Hyperspectral Image Classification","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-16 05:31:50","doi":"10.21203/rs.3.rs-6773180/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":"0b48f974-3271-4185-a36e-4b6002e03dd0","owner":[],"postedDate":"July 16th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-09-07T14:38:42+00:00","versionOfRecord":[],"versionCreatedAt":"2025-07-16 05:31:50","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6773180","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6773180","identity":"rs-6773180","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}