MECA-DETR：Multi-scale Edge-aware Contextual Attention DETR for UAV-based Small Object Detection

MECA-DETR：Multi-scale Edge-aware Contextual Attention DETR for UAV-based Small Object Detection | 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 Article MECA-DETR：Multi-scale Edge-aware Contextual Attention DETR for UAV-based Small Object Detection YuJie Zhao, Biao Li, XueFeng Rao, JinZhen Lu, XiangMeng Pan, WangZhong Li This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7257091/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 Small object detection in UAV aerial imagery remains a persistent challenge due to the need for precise edge preservation, effective multi-scale feature fusion, and maintaining stable, efficient training. To tackle these issues, we propose MECA-DETR, a DETR-based end-to-end detection framework tailored for UAV-based small object detection. MECA-DETR comprises three key components:(1)Multi-Scale Edge Fusion (MSEF) enhances structural representation by integrating multi-scale context with high-frequency edge features; (2)Cross-Scale Attention Fusion (CSAF) leverages a novel attention mechanism that jointly captures local details and global context to align semantics across scales; (3)Adaptive Intermediate Fusion with DynamicTanh (AIFI_DyT) employs a dynamic channel-wise activation in place of LayerNorm, stabilizing training and accelerating convergence without additional computational cost. Extensive experiments on VisDrone2019 and DOTA datasets validate the effectiveness of our approach. On the VisDrone2019 dataset, MECA-DETR achieves 28.7% AP and 40.1% AP50, representing relative improvements of approximately 7.5% and 10.5% over RT-DETR-R18, respectively. On DOTA, MECA-DETR attains 33.55% mAP₀.₅:₀.₉₅, outperforming RT-DETR-R50 by 1.81%. These results highlight the effectiveness of our edge-aware multi-scale design and dynamic activation strategy for efficient small object detection in UAV imagery. Physical sciences/Engineering Physical sciences/Mathematics and computing UAV aerial images Object detection Multi-scale fusion Real-time detection Edge-aware features Dynamic activation 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-7257091","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":497457834,"identity":"e1e008e6-1157-4731-b5fb-32690c09be3f","order_by":0,"name":"YuJie Zhao","email":"","orcid":"","institution":"Guangxi University","correspondingAuthor":false,"prefix":"","firstName":"YuJie","middleName":"","lastName":"Zhao","suffix":""},{"id":497457835,"identity":"a32d4faa-7b90-4189-a39f-c033f5d51aa4","order_by":1,"name":"Biao Li","email":"","orcid":"","institution":"Guangxi University","correspondingAuthor":false,"prefix":"","firstName":"Biao","middleName":"","lastName":"Li","suffix":""},{"id":497457836,"identity":"150d7a6a-6a40-4d33-bc6d-9b4a2c5d9e1b","order_by":2,"name":"XueFeng Rao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAwklEQVRIiWNgGAWjYBCDBAYG5gMHPvwgQikPQgtb4sGZPaRp4TE+zMFGhBZ7ieQNzIVt2/L4pc98OAw0QZ5f7AABWyTSCphntt0uluzL3XC4wILBcObsBEJacgyYedtuJ244w7vh8AwehgSD28Rq2X+G58FhHjZStGzg4WEgUsuZZwXMPOduF0ucYTMABrIEYb+wtwNDjKfsdh5/D/PjDx9+2MjzSxPQwiCQYI4c5RIElIMA/wEDIlSNglEwCkbBiAYA291B2fp5mAYAAAAASUVORK5CYII=","orcid":"","institution":"Guilin University of Aerospace Technology","correspondingAuthor":true,"prefix":"","firstName":"XueFeng","middleName":"","lastName":"Rao","suffix":""},{"id":497457837,"identity":"d64c9ab1-b066-4fe8-ad03-008a53b52174","order_by":3,"name":"JinZhen Lu","email":"","orcid":"","institution":"Guilin Changhai Development Co., Ltd","correspondingAuthor":false,"prefix":"","firstName":"JinZhen","middleName":"","lastName":"Lu","suffix":""},{"id":497457838,"identity":"08f791ca-01f8-40c8-a3ff-e4de993745ba","order_by":4,"name":"XiangMeng Pan","email":"","orcid":"","institution":"Guangxi University","correspondingAuthor":false,"prefix":"","firstName":"XiangMeng","middleName":"","lastName":"Pan","suffix":""},{"id":497457839,"identity":"8699ebb1-8e05-48ec-a3b6-d56ac34a8c64","order_by":5,"name":"WangZhong Li","email":"","orcid":"","institution":"Guangxi University","correspondingAuthor":false,"prefix":"","firstName":"WangZhong","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2025-07-31 01:54:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7257091/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7257091/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":102910189,"identity":"1563e6c6-8267-4c93-a716-88daf69cc792","added_by":"auto","created_at":"2026-02-18 09:57:48","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1549546,"visible":true,"origin":"","legend":"","description":"","filename":"MECADETRword.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7257091/v1_covered_2adf5eed-1da8-4206-91cc-cc0683a1e259.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"MECA-DETR：Multi-scale Edge-aware Contextual Attention DETR for UAV-based Small Object Detection","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":"UAV aerial images, Object detection, Multi-scale fusion, Real-time detection, Edge-aware features, Dynamic activation","lastPublishedDoi":"10.21203/rs.3.rs-7257091/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7257091/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Small object detection in UAV aerial imagery remains a persistent challenge due to the need for precise edge preservation, effective multi-scale feature fusion, and maintaining stable, efficient training. To tackle these issues, we propose MECA-DETR, a DETR-based end-to-end detection framework tailored for UAV-based small object detection. MECA-DETR comprises three key components:(1)Multi-Scale Edge Fusion (MSEF) enhances structural representation by integrating multi-scale context with high-frequency edge features; (2)Cross-Scale Attention Fusion (CSAF) leverages a novel attention mechanism that jointly captures local details and global context to align semantics across scales; (3)Adaptive Intermediate Fusion with DynamicTanh (AIFI_DyT) employs a dynamic channel-wise activation in place of LayerNorm, stabilizing training and accelerating convergence without additional computational cost.\nExtensive experiments on VisDrone2019 and DOTA datasets validate the effectiveness of our approach. On the VisDrone2019 dataset, MECA-DETR achieves 28.7% AP and 40.1% AP50, representing relative improvements of approximately 7.5% and 10.5% over RT-DETR-R18, respectively. On DOTA, MECA-DETR attains 33.55% mAP₀.₅:₀.₉₅, outperforming RT-DETR-R50 by 1.81%. These results highlight the effectiveness of our edge-aware multi-scale design and dynamic activation strategy for efficient small object detection in UAV imagery.","manuscriptTitle":"MECA-DETR：Multi-scale Edge-aware Contextual Attention DETR for UAV-based Small Object Detection","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-13 20:48:52","doi":"10.21203/rs.3.rs-7257091/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":"6a5a993f-91d6-48a8-8110-d603acbbcc0c","owner":[],"postedDate":"August 13th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":52844565,"name":"Physical sciences/Engineering"},{"id":52844566,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-02-18T09:56:40+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-13 20:48:52","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7257091","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7257091","identity":"rs-7257091","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}