UTFormer: A UAV Sensing-based Triple Attention Transformer Network for Semantic Segmentation

UTFormer: A UAV Sensing-based Triple Attention Transformer Network for Semantic Segmentation | 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 UTFormer: A UAV Sensing-based Triple Attention Transformer Network for Semantic Segmentation Da Liu, Hao Long, Zhenbao Liu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4501785/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 Compared to the common urban landscape semantic segmentation, with the impact of flight altitude, UAV image semantic segmentation is more challenging because small targets have a very low percentage of pixels and multi-scale features. Yet, the commonly used successive grid downsampling strategy in the current transformer-based methods omits features of small targets. Furthermore, it leads to even worse results due to the complex background interference. In reaction to this, existing strategies aim to maintain superior resolution. Nevertheless, the application of this method incurs significantly high computational costs which brings challenges to the application of assembling UAVs. So it is significant to design a novel framework to balance retaining more pixels representing small objects during downsampling and fewer computational costs. For this, we propose a UAV Sensing-based Triple Attention Transformer Network (UTFormer), which reduces complexity and enhances the segmentation of small targets simultaneously. During the overlap embedding of feature maps, the model utilizes channel attention to allocate half of the channels for global attention while adaptively selecting important semantic information from the remaining for local attention. So this triple attention strategy not only optimizes computational resources but also improves the model's ability to handle the diverse challenges presented by UAV imagery, ensuring accurate segmentation across varied object scales and densities. Our method shows superior performance on two public datasets: AeroScapes and Vaihingen, achieving 75.57% and 78.93% mean intersection over union. The proposed UTFormer has been released on Github: https://github.com/leoda1/UTFormer . Unmanned Aerial Vehicles Small Targets Remote Sensing Semantic Segmentation 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-4501785","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":311995449,"identity":"d09d66d0-77fd-4da2-812f-eee0a065ff3b","order_by":0,"name":"Da Liu","email":"","orcid":"","institution":"Beijing Union University","correspondingAuthor":false,"prefix":"","firstName":"Da","middleName":"","lastName":"Liu","suffix":""},{"id":311995451,"identity":"91350e5a-3e04-42cc-ac08-ad5db6cf7365","order_by":1,"name":"Hao Long","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6UlEQVRIiWNgGAWjYFCCHAaGB0DKgIGB8TFEJIGgFsaGBIgWZmOStbBJE6VFvj33+IOEijt229kPH6subDvMwM+eY8DwcwduLYw97xIbEs48S97Zk5Z2eyZQi2TPGwPG3jO4tTBL5Bg2JLYdTjY4kGN2mxeoxeBGjgEzYxtuLWxwLeffmBWDtNgT0sID1WIHNNyMGWyLBAEtEjxvDGcknDmcYHDjWbL0jHPpPBJnnhUc7MWjRb49x+DDh4rD9gbnkw9+LiizluNvT9744CceLTCQ2ABzKYg4QFgDA4M9MYpGwSgYBaNghAIAs9ZUtyFDK2MAAAAASUVORK5CYII=","orcid":"","institution":"Beijing Union University","correspondingAuthor":true,"prefix":"","firstName":"Hao","middleName":"","lastName":"Long","suffix":""},{"id":311995453,"identity":"bb1889ca-861a-4d3b-b4d2-8079e2374db6","order_by":2,"name":"Zhenbao Liu","email":"","orcid":"","institution":"Northwestern Polytechnical University","correspondingAuthor":false,"prefix":"","firstName":"Zhenbao","middleName":"","lastName":"Liu","suffix":""}],"badges":[],"createdAt":"2024-05-30 09:10:45","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4501785/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4501785/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":59035364,"identity":"7fd10dc8-743f-4317-958a-b4948e65eff2","added_by":"auto","created_at":"2024-06-25 14:59:35","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4462172,"visible":true,"origin":"","legend":"","description":"","filename":"snarticletemplate.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4501785/v1_covered_e702b7d4-e76d-4d20-b058-2207353c5790.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"UTFormer: A UAV Sensing-based Triple Attention Transformer Network for Semantic Segmentation","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":"Unmanned Aerial Vehicles, Small Targets, Remote Sensing, Semantic Segmentation","lastPublishedDoi":"10.21203/rs.3.rs-4501785/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4501785/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Compared to the common urban landscape semantic segmentation, with the impact of flight altitude, UAV image semantic segmentation is more challenging because small targets have a very low percentage of pixels and multi-scale features. Yet, the commonly used successive grid downsampling strategy in the current transformer-based methods omits features of small targets. Furthermore, it leads to even worse results due to the complex background interference. In reaction to this, existing strategies aim to maintain superior resolution. Nevertheless, the application of this method incurs significantly high computational costs which brings challenges to the application of assembling UAVs. So it is significant to design a novel framework to balance retaining more pixels representing small objects during downsampling and fewer computational costs. For this, we propose a UAV Sensing-based Triple Attention Transformer Network (UTFormer), which reduces complexity and enhances the segmentation of small targets simultaneously. During the overlap embedding of feature maps, the model utilizes channel attention to allocate half of the channels for global attention while adaptively selecting important semantic information from the remaining for local attention. So this triple attention strategy not only optimizes computational resources but also improves the model's ability to handle the diverse challenges presented by UAV imagery, ensuring accurate segmentation across varied object scales and densities. Our method shows superior performance on two public datasets: AeroScapes and Vaihingen, achieving 75.57\\% and 78.93\\% mean intersection over union. The proposed UTFormer has been released on Github:https://github.com/leoda1/UTFormer.","manuscriptTitle":"UTFormer: A UAV Sensing-based Triple Attention Transformer Network for Semantic Segmentation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-06-13 17:11:55","doi":"10.21203/rs.3.rs-4501785/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":"20f47c0a-f260-4ff0-9f79-cd2f3a68e7ff","owner":[],"postedDate":"June 13th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-06-25T14:51:26+00:00","versionOfRecord":[],"versionCreatedAt":"2024-06-13 17:11:55","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4501785","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4501785","identity":"rs-4501785","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}