Cascaded Dual-Directional Cross-Attention Transformer Network for Hyperspectral Imaging Classification

preprint OA: closed
Full text JSON View at publisher

Abstract

Abstract Hyperspectral image classification faces challenges of inadequate utilization of spectral information and insufficient extraction of spatial features. Traditional methods often overly rely on high-reflectance bands while neglecting crucial spectral information in low-reflectance bands. This can lead to degraded classification performance for category information under small-sample conditions, resulting in limited classification results. To address this issue, this paper proposes a Cascaded Dual-Directional Cross-Attention Transformer Network for Hyperspectral Imaging Classification(CDCATNet). The network fully exploits spectral-spatial complementary information with a small number of labeled samples through a Dual-Directional Cross-Attention (DCA) module; it enhances feature extraction by employing cross-branch interaction and a multi-scale local-global fusion unit; finally, it achieves long-range dependency modeling and feature fusion through a lightweight transformer. Experiments on four publicly available datasets demonstrate that CDCATNet outperforms existing mainstream methods in terms of overall accuracy, average accuracy, and Kappa coefficient, exhibiting excellent classification performance and generalization ability.
Full text 26,322 characters · extracted from preprint-html · click to expand
Cascaded Dual-Directional Cross-Attention Transformer Network for Hyperspectral Imaging 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 Cascaded Dual-Directional Cross-Attention Transformer Network for Hyperspectral Imaging Classification Songpeng Gong, Uzair Aslam Bhatti This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7961157/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 11 You are reading this latest preprint version Abstract Hyperspectral image classification faces challenges of inadequate utilization of spectral information and insufficient extraction of spatial features. Traditional methods often overly rely on high-reflectance bands while neglecting crucial spectral information in low-reflectance bands. This can lead to degraded classification performance for category information under small-sample conditions, resulting in limited classification results. To address this issue, this paper proposes a Cascaded Dual-Directional Cross-Attention Transformer Network for Hyperspectral Imaging Classification(CDCATNet). The network fully exploits spectral-spatial complementary information with a small number of labeled samples through a Dual-Directional Cross-Attention (DCA) module; it enhances feature extraction by employing cross-branch interaction and a multi-scale local-global fusion unit; finally, it achieves long-range dependency modeling and feature fusion through a lightweight transformer. Experiments on four publicly available datasets demonstrate that CDCATNet outperforms existing mainstream methods in terms of overall accuracy, average accuracy, and Kappa coefficient, exhibiting excellent classification performance and generalization ability. Dual-Directional Cross-Attention(DCA) hyperspectral imag- ing(HSI) local-global fusion cross-branch interaction Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 29 Mar, 2026 Reviews received at journal 28 Mar, 2026 Reviewers agreed at journal 10 Mar, 2026 Reviewers agreed at journal 08 Mar, 2026 Reviews received at journal 21 Nov, 2025 Reviewers agreed at journal 19 Nov, 2025 Reviewers agreed at journal 19 Nov, 2025 Reviewers invited by journal 19 Nov, 2025 Editor assigned by journal 08 Nov, 2025 Submission checks completed at journal 29 Oct, 2025 First submitted to journal 27 Oct, 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-7961157","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":549367719,"identity":"392c818e-c78b-4456-ac4b-0ec4ab9a213a","order_by":0,"name":"Songpeng Gong","email":"","orcid":"","institution":"Hainan University","correspondingAuthor":false,"prefix":"","firstName":"Songpeng","middleName":"","lastName":"Gong","suffix":""},{"id":549367720,"identity":"d7d7fa25-2463-4da6-af39-7fe2c1ef8ce4","order_by":1,"name":"Uzair Aslam Bhatti","email":"data:image/png;base64,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","orcid":"","institution":"Hainan University","correspondingAuthor":true,"prefix":"","firstName":"Uzair","middleName":"Aslam","lastName":"Bhatti","suffix":""}],"badges":[],"createdAt":"2025-10-27 14:36:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7961157/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7961157/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":96895801,"identity":"b98e325d-67ff-404c-a815-881059156532","added_by":"auto","created_at":"2025-11-27 10:20:34","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4154,"visible":true,"origin":"","legend":"","description":"","filename":"ffd6da7c82004d938026dc792401ca6b.json","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/42ee2e0fe3326b7537e92cd9.json"},{"id":96919595,"identity":"04099dd1-6451-4fcc-8e9d-d8e68851535a","added_by":"auto","created_at":"2025-11-27 14:14:11","extension":"jpg","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1129551,"visible":true,"origin":"","legend":"","description":"","filename":"1Untitledslide.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/e82a6628c6bd321db95a5101.jpg"},{"id":96895802,"identity":"96f926de-deeb-47df-a836-5a12354a8f18","added_by":"auto","created_at":"2025-11-27 10:20:34","extension":"jpg","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":520023,"visible":true,"origin":"","legend":"","description":"","filename":"Batchsize.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/6092c7f6b1a5a8921132c5b9.jpg"},{"id":96895800,"identity":"4f9f72d4-ff4e-4419-beb3-36a31fc3361a","added_by":"auto","created_at":"2025-11-27 10:20:34","extension":"jpg","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":143171,"visible":true,"origin":"","legend":"","description":"","filename":"CDCA.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/e6f5677429d27c6f25d1dfc1.jpg"},{"id":96895803,"identity":"944d834b-082a-4ed4-903f-1ea5deb8f0b3","added_by":"auto","created_at":"2025-11-27 10:20:34","extension":"jpg","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1089805,"visible":true,"origin":"","legend":"","description":"","filename":"CDCATNet.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/578fae7c1c4f545844c927e9.jpg"},{"id":96920494,"identity":"d5dc6d8e-d2c5-485a-9fc3-5cf2699ed9bd","added_by":"auto","created_at":"2025-11-27 14:15:13","extension":"jpeg","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":134034,"visible":true,"origin":"","legend":"","description":"","filename":"CrossInteraction.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/0b4af152bc84a82f2c7d1fe6.jpeg"},{"id":96920619,"identity":"54225ee8-3874-4efe-b946-695ffb4618f3","added_by":"auto","created_at":"2025-11-27 14:15:19","extension":"jpg","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":975740,"visible":true,"origin":"","legend":"","description":"","filename":"DCA.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/35773a426d5037413aa3b7e9.jpg"},{"id":96919564,"identity":"7caea3e8-b799-439c-abd1-73c9d3389134","added_by":"auto","created_at":"2025-11-27 14:14:06","extension":"jpg","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":682752,"visible":true,"origin":"","legend":"","description":"","filename":"LR.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/bd4a3142ce63ad49320ced44.jpg"},{"id":96920710,"identity":"40f404e9-a53f-4e98-94e4-fd07a9f272ee","added_by":"auto","created_at":"2025-11-27 14:15:22","extension":"pdf","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":16205722,"visible":true,"origin":"","legend":"","description":"","filename":"LaTeXCDCANet.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/1e254192dccf5f4724d778f0.pdf"},{"id":96920514,"identity":"ab183972-1b3b-4a0d-b032-78f464d446f0","added_by":"auto","created_at":"2025-11-27 14:15:14","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":334663,"visible":true,"origin":"","legend":"","description":"","filename":"Salinasgt.png","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/48e95a1e64d0a66a244b7a69.png"},{"id":96895807,"identity":"b6abc93f-c4f7-4b7c-a0b3-41b8f77847fe","added_by":"auto","created_at":"2025-11-27 10:20:34","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":249977,"visible":true,"origin":"","legend":"","description":"","filename":"WHUHiHanChuangt.png","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/86c4bb73267177dcc4b35ab8.png"},{"id":96895811,"identity":"e8834c4c-8871-4757-8570-c8935f5792d7","added_by":"auto","created_at":"2025-11-27 10:20:34","extension":"jpg","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":774125,"visible":true,"origin":"","legend":"","description":"","filename":"epochs.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/658904cd44a58b344d815e30.jpg"},{"id":96920308,"identity":"4f762981-e45b-4fb6-ad82-48d071f70df0","added_by":"auto","created_at":"2025-11-27 14:15:03","extension":"eps","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":304,"visible":true,"origin":"","legend":"","description":"","filename":"example.eps","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/e79925774a765a866bfa22ff.eps"},{"id":96919986,"identity":"46733d52-25a2-47c3-ab60-aa17d94a1367","added_by":"auto","created_at":"2025-11-27 14:14:40","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3222419,"visible":true,"origin":"","legend":"","description":"","filename":"fig10.png","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/9514037cdfa77f79d7a50c47.png"},{"id":96919593,"identity":"62843b7f-35c3-49d3-ae3e-18588668b697","added_by":"auto","created_at":"2025-11-27 14:14:11","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2630693,"visible":true,"origin":"","legend":"","description":"","filename":"fig14.png","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/5d1fe3fec439d440c920a787.png"},{"id":96921094,"identity":"aff54e11-57ed-4c00-881c-53f9717cb177","added_by":"auto","created_at":"2025-11-27 14:15:41","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1433381,"visible":true,"origin":"","legend":"","description":"","filename":"fig7.png","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/6b8ffb80662ac40950612748.png"},{"id":96920616,"identity":"46e4c153-bd11-4c27-8713-8d615b53c05b","added_by":"auto","created_at":"2025-11-27 14:15:19","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1162509,"visible":true,"origin":"","legend":"","description":"","filename":"fig8.png","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/0b597d8f8320e203e5237e7b.png"},{"id":96895816,"identity":"b291019e-9869-4f05-87a1-6a9e02ecb97d","added_by":"auto","created_at":"2025-11-27 10:20:34","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1239659,"visible":true,"origin":"","legend":"","description":"","filename":"fig9.png","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/40e4a0abcffba1ad3d9177d6.png"},{"id":96920872,"identity":"943d095b-52fd-4d57-9405-95ef1cfd421d","added_by":"auto","created_at":"2025-11-27 14:15:28","extension":"txt","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1582,"visible":true,"origin":"","legend":"","description":"","filename":"history.txt","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/eb1c75a9b7665ecfd7afeeb2.txt"},{"id":96895813,"identity":"71bfdbe9-149b-4368-90d3-88e089302d83","added_by":"auto","created_at":"2025-11-27 10:20:34","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":227174,"visible":true,"origin":"","legend":"","description":"","filename":"houstongt.png","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/75b8bd2bc3479fa9593e9ba1.png"},{"id":96920803,"identity":"e111fe5a-0d77-4d6c-9cec-0e501ed80bbc","added_by":"auto","created_at":"2025-11-27 14:15:26","extension":"jpg","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":755805,"visible":true,"origin":"","legend":"","description":"","filename":"patchsize.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/90014831a050cba54f7b542f.jpg"},{"id":96920893,"identity":"a23c203e-7b2c-4df8-be29-207f754c477c","added_by":"auto","created_at":"2025-11-27 14:15:29","extension":"txt","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1707,"visible":true,"origin":"","legend":"","description":"","filename":"readme.txt","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/002b63c59af281f9ea5e3def.txt"},{"id":96895809,"identity":"b62b9ebc-f091-49c8-b4ea-34299a8a4139","added_by":"auto","created_at":"2025-11-27 10:20:34","extension":"bst","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":33238,"visible":true,"origin":"","legend":"","description":"","filename":"spbasic.bst","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/996465b385bbe990c6b10dbd.bst"},{"id":96920912,"identity":"d905eec0-96e2-4ddb-a890-9fbd94e6d223","added_by":"auto","created_at":"2025-11-27 14:15:30","extension":"bst","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":30130,"visible":true,"origin":"","legend":"","description":"","filename":"spmpsci.bst","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/78a5e9f23938863ac86a5c71.bst"},{"id":96895829,"identity":"2b2391d6-c24e-4bd9-9e4a-30daf8a1092c","added_by":"auto","created_at":"2025-11-27 10:20:35","extension":"bst","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":28600,"visible":true,"origin":"","legend":"","description":"","filename":"spphys.bst","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/7c66c0f9d24e5f45e14ff755.bst"},{"id":96895822,"identity":"7be8d22e-13dd-401e-9a56-9bb8ee87f72b","added_by":"auto","created_at":"2025-11-27 10:20:35","extension":"clo","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3809,"visible":true,"origin":"","legend":"","description":"","filename":"svglov3.clo","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/c61ea75d394ba0be07a9eb3d.clo"},{"id":96895827,"identity":"67f3ccdc-6bcc-40ca-98a1-88a54e76cd5f","added_by":"auto","created_at":"2025-11-27 10:20:35","extension":"cls","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":47679,"visible":true,"origin":"","legend":"","description":"","filename":"svjour3.cls","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/f8aac21535e7b1e548dbfdf4.cls"},{"id":96919643,"identity":"93973d43-91f4-48a2-9cf3-08be264eca28","added_by":"auto","created_at":"2025-11-27 14:14:15","extension":"aux","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8383,"visible":true,"origin":"","legend":"","description":"","filename":"template.aux","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/f6700bfebe2f74ab5eb18287.aux"},{"id":96895833,"identity":"94c2730e-800c-41c3-a70f-e9b875c4e7a1","added_by":"auto","created_at":"2025-11-27 10:20:35","extension":"log","order_by":28,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":18149,"visible":true,"origin":"","legend":"","description":"","filename":"template.log","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/4d16961e626c8871e56093f0.log"},{"id":96895837,"identity":"2497db93-98ab-4f07-a24e-dd83d9f5588f","added_by":"auto","created_at":"2025-11-27 10:20:35","extension":"pdf","order_by":29,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":15996367,"visible":true,"origin":"","legend":"","description":"","filename":"template.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/54feec5d7c9240792b042556.pdf"},{"id":96895824,"identity":"f71e2138-366d-4eae-852d-18bc06f9a6ce","added_by":"auto","created_at":"2025-11-27 10:20:35","extension":"gz","order_by":30,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":175559,"visible":true,"origin":"","legend":"","description":"","filename":"template.synctex.gz","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/2987dddc149d54929bc18318.gz"},{"id":96895828,"identity":"fb0b0317-8d2c-4aed-9c49-f51bd4b6e751","added_by":"auto","created_at":"2025-11-27 10:20:35","extension":"dvi","order_by":31,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":50988,"visible":true,"origin":"","legend":"","description":"","filename":"usrguid3.dvi","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/d1b98fc33c7d07519ad53bcd.dvi"},{"id":96895826,"identity":"ad87cd31-5d0b-4743-a038-b601e023a2d9","added_by":"auto","created_at":"2025-11-27 10:20:35","extension":"pdf","order_by":32,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":190374,"visible":true,"origin":"","legend":"","description":"","filename":"usrguid3.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/933f180ed589160cafbce1f8.pdf"},{"id":96895831,"identity":"e74168b7-4a8e-48ab-a5e9-16c18777ca88","added_by":"auto","created_at":"2025-11-27 10:20:35","extension":"png","order_by":33,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":167103,"visible":true,"origin":"","legend":"","description":"","filename":"xuzhougt.png","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/a069f6e4fab037dc128ab8ab.png"},{"id":96895832,"identity":"87df4d24-80c9-4fc1-aeab-f9605c95533f","added_by":"auto","created_at":"2025-11-27 10:20:35","extension":"xml","order_by":34,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":74664,"visible":true,"origin":"","legend":"","description":"","filename":"ffd6da7c82004d938026dc792401ca6b1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1/8833adf615ddacf998519067.xml"},{"id":97135760,"identity":"8616e440-c3d0-4ef2-a336-d3be5f34a283","added_by":"auto","created_at":"2025-12-01 09:53:24","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":16254210,"visible":true,"origin":"","legend":"","description":"","filename":"LaTeXCDCANet.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7961157/v1_covered_eac52f8b-48ce-4917-869d-5cb288e4a097.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Cascaded Dual-Directional Cross-Attention Transformer Network for Hyperspectral Imaging Classification","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":"nonlinear-dynamics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"nody","sideBox":"Learn more about [Nonlinear Dynamics](https://www.springer.com/journal/11071)","snPcode":"11071","submissionUrl":"https://submission.nature.com/new-submission/11071/3","title":"Nonlinear Dynamics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Dual-Directional Cross-Attention(DCA), hyperspectral imag- ing(HSI), local-global fusion, cross-branch interaction","lastPublishedDoi":"10.21203/rs.3.rs-7961157/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7961157/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Hyperspectral image classification faces challenges of inadequate utilization of spectral information and insufficient extraction of spatial features. Traditional methods often overly rely on high-reflectance bands while neglecting crucial spectral information in low-reflectance bands. This can lead to degraded classification performance for category information under small-sample conditions, resulting in limited classification results. To address this issue, this paper proposes a Cascaded Dual-Directional Cross-Attention Transformer Network for Hyperspectral Imaging Classification(CDCATNet). The network fully exploits spectral-spatial complementary information with a small number of labeled samples through a Dual-Directional Cross-Attention (DCA) module; it enhances feature extraction by employing cross-branch interaction and a multi-scale local-global fusion unit; finally, it achieves long-range dependency modeling and feature fusion through a lightweight transformer. Experiments on four publicly available datasets demonstrate that CDCATNet outperforms existing mainstream methods in terms of overall accuracy, average accuracy, and Kappa coefficient, exhibiting excellent classification performance and generalization ability.","manuscriptTitle":"Cascaded Dual-Directional Cross-Attention Transformer Network for Hyperspectral Imaging Classification","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-27 10:20:30","doi":"10.21203/rs.3.rs-7961157/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-03-29T05:32:40+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-29T01:08:07+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"295567969795394246173252013711800788682","date":"2026-03-10T18:11:55+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"300071619148170346318159292343706942935","date":"2026-03-08T15:06:37+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-21T15:19:26+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"180924939493023560521665005806478345465","date":"2025-11-19T15:18:51+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"256704940431824616701655680222829286752","date":"2025-11-19T14:41:19+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-11-19T13:05:57+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-11-08T19:08:27+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-10-29T04:23:44+00:00","index":"","fulltext":""},{"type":"submitted","content":"Nonlinear Dynamics","date":"2025-10-27T13:09:23+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nonlinear-dynamics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"nody","sideBox":"Learn more about [Nonlinear Dynamics](https://www.springer.com/journal/11071)","snPcode":"11071","submissionUrl":"https://submission.nature.com/new-submission/11071/3","title":"Nonlinear Dynamics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"f0e4dc1c-bde7-456f-9455-925b16d21d15","owner":[],"postedDate":"November 27th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-04-28T08:40:36+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-27 10:20:30","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7961157","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7961157","identity":"rs-7961157","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.

My notes (saved in your browser only)

Ask this paper AI returns verbatim quotes from the full text · source: preprint-html

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2025) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

europepmc
last seen: 2026-05-20T01:45:00.602351+00:00