EADI-YOLO: a lightweight and efficient model for rail surface defect detection

EADI-YOLO: a lightweight and efficient model for rail surface defect 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 Research Article EADI-YOLO: a lightweight and efficient model for rail surface defect detection Siwei Ma, Ronghua Li, Henan Hu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7183947/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 As the complexity of railway transportation systems increases, higher demands have been placed on the real-time performance and accuracy of track defect detection, making traditional methods inadequate for intelligent inspection tasks. To address this, this paper proposes a lightweight and efficient improved detection model, EADI-YOLO, based on the YOLOv10n framework, aiming to achieve the optimal balance between detection accuracy, inference speed, and computational cost. The model integrates the C2f-EMAN module into the backbone, combining EMA and NAM attention mechanisms to enhance the representation of key regional features. It adopts the efficient AKConv module to replace standard convolutions, improving multi-scale defect perception while reducing parameter overhead. Furthermore, a DySample dynamic sampling module is introduced in the upsampling stage to better reconstruct feature details and preserve semantic information. An Inner-GIoU regression loss function is designed to optimize bounding box localization accuracy.Experimental results on rail surface defect detection tasks demonstrate the effectiveness of the proposed model. EADI-YOLO achieves a [email protected] of 90.3% and a [email protected] :0.95 of 49.1%, with an inference speed of 120 FPS, representing improvements of 2.8%, 6.7%, and 15 FPS over YOLOv10n, respectively. Compared to other mainstream detection models such as RT-DETR and YOLOv13n, EADI-YOLO demonstrates superior detection accuracy while maintaining excellent lightweight and real-time performance. Generalization experiments show that EADI-YOLO maintains an excellent balance between accuracy, speed, and model complexity across different rail defect datasets, making it suitable for intelligent detection of railway track defects. Rail surface defect detection EADI-YOLO Attention mechanism Lightweight convolution Dynamic sampling Bounding box regression 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-7183947","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":491544194,"identity":"80221cbc-e824-45c1-9027-6400e1541ef1","order_by":0,"name":"Siwei Ma","email":"","orcid":"","institution":"Dalian Jiaotong University","correspondingAuthor":false,"prefix":"","firstName":"Siwei","middleName":"","lastName":"Ma","suffix":""},{"id":491544195,"identity":"809befaa-405c-4ada-9227-7fb1c9e190db","order_by":1,"name":"Ronghua Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3klEQVRIie3PMQrCMBSA4RcC6ZLaVSjiFSIBdSjepRQyOXiEuOhSdK2LXkFvoD7s5AE6OCgF544iHZQO4tR0FMy/ZHkfeQ/AZvvBWrR69gDd27woRDAyEvYhEKUkmajITOBDlKK8OBJtJI57yyfPS7jU534eiD0FB0/b+sUcKVeLe5gc4oEci0sLuFJZPWHMd2MMNXLhj8WdQpv3m5FN+iZDgUQ3IvyB4fbMlA8NCZWuRrnLKPZioSJmusXzUpLzEjvrjEyvjzIYeQ6mtaSKzL7/NY5Xlc3GbDab7U97AS3gSApb8W5ZAAAAAElFTkSuQmCC","orcid":"","institution":"Dalian Jiaotong University","correspondingAuthor":true,"prefix":"","firstName":"Ronghua","middleName":"","lastName":"Li","suffix":""},{"id":491544196,"identity":"276ca5a8-5e67-48eb-96c6-c3bb9e901b38","order_by":2,"name":"Henan Hu","email":"","orcid":"","institution":"Dalian Jiaotong University","correspondingAuthor":false,"prefix":"","firstName":"Henan","middleName":"","lastName":"Hu","suffix":""}],"badges":[],"createdAt":"2025-07-22 07:38:17","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7183947/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7183947/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":95801746,"identity":"ac645e34-a366-48d2-9de4-66217bdffb75","added_by":"auto","created_at":"2025-11-13 08:26:06","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":835290,"visible":true,"origin":"","legend":"","description":"","filename":"EADIYOLOalightweightandefficientmodelforrailsurfacedefectdetection.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7183947/v1_covered_43038853-4386-4886-9480-c2b325fdbe0c.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"EADI-YOLO: a lightweight and efficient model for rail surface defect detection","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"Rail surface defect detection, EADI-YOLO, Attention mechanism, Lightweight convolution, Dynamic sampling, Bounding box regression","lastPublishedDoi":"10.21203/rs.3.rs-7183947/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7183947/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAs the complexity of railway transportation systems increases, higher demands have been placed on the real-time performance and accuracy of track defect detection, making traditional methods inadequate for intelligent inspection tasks. To address this, this paper proposes a lightweight and efficient improved detection model, EADI-YOLO, based on the YOLOv10n framework, aiming to achieve the optimal balance between detection accuracy, inference speed, and computational cost. The model integrates the C2f-EMAN module into the backbone, combining EMA and NAM attention mechanisms to enhance the representation of key regional features. It adopts the efficient AKConv module to replace standard convolutions, improving multi-scale defect perception while reducing parameter overhead. Furthermore, a DySample dynamic sampling module is introduced in the upsampling stage to better reconstruct feature details and preserve semantic information. An Inner-GIoU regression loss function is designed to optimize bounding box localization accuracy.Experimental results on rail surface defect detection tasks demonstrate the effectiveness of the proposed model. EADI-YOLO achieves a [email protected] of 90.3% and a [email protected]:0.95 of 49.1%, with an inference speed of 120 FPS, representing improvements of 2.8%, 6.7%, and 15 FPS over YOLOv10n, respectively. Compared to other mainstream detection models such as RT-DETR and YOLOv13n, EADI-YOLO demonstrates superior detection accuracy while maintaining excellent lightweight and real-time performance. Generalization experiments show that EADI-YOLO maintains an excellent balance between accuracy, speed, and model complexity across different rail defect datasets, making it suitable for intelligent detection of railway track defects.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e","manuscriptTitle":"EADI-YOLO: a lightweight and efficient model for rail surface defect detection","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-01 09:17:50","doi":"10.21203/rs.3.rs-7183947/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":"01e3be81-292f-4453-925c-35eb7852f4b9","owner":[],"postedDate":"August 1st, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-11-12T18:08:49+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-01 09:17:50","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7183947","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7183947","identity":"rs-7183947","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}