A lightweight enhanced branching attention model for remote sensing scene image classification

A lightweight enhanced branching attention model for remote sensing scene 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 A lightweight enhanced branching attention model for remote sensing scene image classification Huiyue Wang, Xinyu Wang, Haixia Xu, LiMing Yuan, Xianbin Wen This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4644476/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 17 Nov, 2025 Read the published version in Earth Science Informatics → Version 1 posted 9 You are reading this latest preprint version Abstract Unlike natural images, remote sensing images exhibit significant spatial complexity and minimal intra-class differences, presenting considerable challenges in the field of remote sensing scene image classification (RSSC). Although existing convolutional neural networks have achieved some progress in this domain, they often fail to fully account for the unique characteristics of remote sensing images. Additionally, these networks typically suffer from excessive parameter redundancy, resulting in substantial computational burdens. This is particularly problematic given the difficulty in obtaining and labeling remote sensing data. To address these issues, this paper proposes a lightweight method (AEBANet) featuring an attention branching structure specifically designed for RSSC. First, we construct an overall feature extraction framework based on depth-wise separable convolution (DS-Conv) to ensure efficient feature extraction while maintaining accuracy. Then, we propose the Adaptive Enhanced Branch Attention (AEBA) module, a lightweight structural design that enhances the model's capability to capture key features in both channel and spatial domains. Second, we develop the Multi-Level Feature Fusion (MLFF) module to integrate features at different levels, thereby improving information flow between features and utilizing detailed shallow information to supervise the deep global information. Finally, the proposed AEBANet achieves the highest overall accuracy of 93.12%, 96.76%, and 99.52% on the NWPU, AID, and UCM datasets, respectively. Ablation studies on these datasets validate the effectiveness and necessity of each module. Additionally, the proposed method is characterized by low complexity and computational cost. Convolutional neural network (CNN) attention mechanism feature fusion remote sensing scene classification(RSSC) Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 17 Nov, 2025 Read the published version in Earth Science Informatics → Version 1 posted Editorial decision: Revision requested 24 Aug, 2025 Reviews received at journal 23 Aug, 2025 Reviewers agreed at journal 23 Aug, 2025 Reviews received at journal 27 Jul, 2024 Reviewers agreed at journal 07 Jul, 2024 Reviewers invited by journal 06 Jul, 2024 Editor assigned by journal 06 Jul, 2024 Submission checks completed at journal 03 Jul, 2024 First submitted to journal 26 Jun, 2024 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-4644476","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":328385056,"identity":"496d3f94-a54a-477f-b839-70a903c2ce63","order_by":0,"name":"Huiyue Wang","email":"","orcid":"","institution":"Ministry of Education, Tianjin University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Huiyue","middleName":"","lastName":"Wang","suffix":""},{"id":328385057,"identity":"1d295f84-424a-48d8-adb7-dbb932637e47","order_by":1,"name":"Xinyu Wang","email":"","orcid":"","institution":"Ministry of Education, Tianjin University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Xinyu","middleName":"","lastName":"Wang","suffix":""},{"id":328385058,"identity":"c9f91486-6f8d-4f2f-a7f3-89d1e2799b9a","order_by":2,"name":"Haixia Xu","email":"","orcid":"","institution":"Ministry of Education, Tianjin University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Haixia","middleName":"","lastName":"Xu","suffix":""},{"id":328385059,"identity":"c6214d43-80ad-4d26-a6fd-6ec3baa898e8","order_by":3,"name":"LiMing Yuan","email":"","orcid":"","institution":"Ministry of Education, Tianjin University of Technology","correspondingAuthor":false,"prefix":"","firstName":"LiMing","middleName":"","lastName":"Yuan","suffix":""},{"id":328385060,"identity":"e23644c3-d9d4-45c8-8951-0c81b4eeeecd","order_by":4,"name":"Xianbin Wen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAw0lEQVRIiWNgGAWjYDACCRBRwcAM5vAQr+WMATMDG0laGNsMGIjXYnC7x/Bx4bw/7Ab3GxgfvG1jkDcnpEVyzhlj45nbDJgNjjEwG85tYzDc2UBAC79E7jZpXogWNmneNoYEgwMEtLBJ5G7/zTsHrIX9N1FaQLYw8zZAbGEmSovknPOfpXmOGTNLHktslpxzTsJwAyEtBrfbEj/z1Mgl8x0+fPDDmzIbeYK2wEAyMHYaGKAxSxywI17pKBgFo2AUjDgAAPJPN6s/T2J4AAAAAElFTkSuQmCC","orcid":"","institution":"Ministry of Education, Tianjin University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Xianbin","middleName":"","lastName":"Wen","suffix":""}],"badges":[],"createdAt":"2024-06-26 18:38:19","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4644476/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4644476/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s12145-025-02031-4","type":"published","date":"2025-11-17T15:58:50+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":96650367,"identity":"1a902bc4-e982-4344-b79f-d171cd501e9e","added_by":"auto","created_at":"2025-11-24 16:11:34","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1857652,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4644476/v1_covered_69c9d2cd-a2e7-47a3-bb33-3ae2ea75f102.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A lightweight enhanced branching attention model for remote sensing scene image 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":"earth-science-informatics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"esin","sideBox":"Learn more about [Earth Science Informatics](http://link.springer.com/journal/12145)","snPcode":"12145","submissionUrl":"https://submission.nature.com/new-submission/12145/3","title":"Earth Science Informatics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Convolutional neural network (CNN), attention mechanism, feature fusion, remote sensing scene classification(RSSC)","lastPublishedDoi":"10.21203/rs.3.rs-4644476/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4644476/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eUnlike natural images, remote sensing images exhibit significant spatial complexity and minimal intra-class differences, presenting considerable challenges in the field of remote sensing scene image classification (RSSC). Although existing convolutional neural networks have achieved some progress in this domain, they often fail to fully account for the unique characteristics of remote sensing images. Additionally, these networks typically suffer from excessive parameter redundancy, resulting in substantial computational burdens. This is particularly problematic given the difficulty in obtaining and labeling remote sensing data. To address these issues, this paper proposes a lightweight method (AEBANet) featuring an attention branching structure specifically designed for RSSC. First, we construct an overall feature extraction framework based on depth-wise separable convolution (DS-Conv) to ensure efficient feature extraction while maintaining accuracy. Then, we propose the Adaptive Enhanced Branch Attention (AEBA) module, a lightweight structural design that enhances the model's capability to capture key features in both channel and spatial domains. Second, we develop the Multi-Level Feature Fusion (MLFF) module to integrate features at different levels, thereby improving information flow between features and utilizing detailed shallow information to supervise the deep global information. Finally, the proposed AEBANet achieves the highest overall accuracy of 93.12%, 96.76%, and 99.52% on the NWPU, AID, and UCM datasets, respectively. Ablation studies on these datasets validate the effectiveness and necessity of each module. Additionally, the proposed method is characterized by low complexity and computational cost.\u003c/p\u003e","manuscriptTitle":"A lightweight enhanced branching attention model for remote sensing scene image classification","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-07-25 10:53:28","doi":"10.21203/rs.3.rs-4644476/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-08-24T21:38:01+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-08-24T02:59:02+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"23017734037112079400668463270061437448","date":"2025-08-23T14:02:51+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-07-27T07:49:58+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"46204461716257915979425293122918081825","date":"2024-07-07T07:23:56+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-07-06T11:43:25+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-07-06T11:42:02+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-07-03T15:09:41+00:00","index":"","fulltext":""},{"type":"submitted","content":"Earth Science Informatics","date":"2024-06-26T18:26:17+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"earth-science-informatics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"esin","sideBox":"Learn more about [Earth Science Informatics](http://link.springer.com/journal/12145)","snPcode":"12145","submissionUrl":"https://submission.nature.com/new-submission/12145/3","title":"Earth Science Informatics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"c5f0db08-0c8f-44ec-bd62-d9cb5833353c","owner":[],"postedDate":"July 25th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-11-24T16:07:25+00:00","versionOfRecord":{"articleIdentity":"rs-4644476","link":"https://doi.org/10.1007/s12145-025-02031-4","journal":{"identity":"earth-science-informatics","isVorOnly":false,"title":"Earth Science Informatics"},"publishedOn":"2025-11-17 15:58:50","publishedOnDateReadable":"November 17th, 2025"},"versionCreatedAt":"2024-07-25 10:53:28","video":"","vorDoi":"10.1007/s12145-025-02031-4","vorDoiUrl":"https://doi.org/10.1007/s12145-025-02031-4","workflowStages":[]},"version":"v1","identity":"rs-4644476","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4644476","identity":"rs-4644476","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}