AFF-LightNet: Attentional Feature Fusion Based Lightweight Network for Ship Detection

AFF-LightNet: Attentional Feature Fusion Based Lightweight Network for Ship 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 AFF-LightNet: Attentional Feature Fusion Based Lightweight Network for Ship Detection yingxiu Yuan, Xiaoyan Yu, Xianwei Rong, Xiaozhou Wang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5369748/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 Efficient mobile detection equipment plays a vital role in ensuring maritime safety, and accurate ship identification is crucial for maritime traffic. Recently, advanced learning-based methods boost the accuracy of ship detection, but face challenges on mobile devices due to size and computation. Thus, we propose a lightweight ship detection network based on feature fusion, called AFF-LightNet. We introduce iterative attentional feature fusion (IAFF) into the proposed neck network, improving the efficiency of feature fusion by introducing a multi-scale channel attention module. Also, Conv is replaced by DCNv2 in the backbone network to further improve the detection accuracy of the proposed network. DCNv2 enhances the spatial sampling position in convolution and Rol pooling by introducing offsets. Moreover, a lightweight convolution GhostConv was introduced into the head network to reduce the number of parameters and computation cost. Last, SIOU was leveraged to improve the convergence speed of the model. We conduct extensive experiments on the publicly available dataset SeaShips and compare it with existing methods. The experimental results show that compared with the standard YOLOv8n, the improved network has an average accuracy of 98.8%, an increase of 0.4%, a reduction of 1.9 G in computational complexity, and a reduction of 0.19 M in parameter count. Physical sciences/Mathematics and computing/Computational science Physical sciences/Mathematics and computing/Computer science Ship detection Deep learning Attentional feature fusion Lightweight 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-5369748","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":375738481,"identity":"bdf5e5a0-5b93-4a2b-a73e-644574b75a6b","order_by":0,"name":"yingxiu Yuan","email":"","orcid":"","institution":"Harbin Normal University","correspondingAuthor":false,"prefix":"","firstName":"yingxiu","middleName":"","lastName":"Yuan","suffix":""},{"id":375738482,"identity":"992bb659-af88-40c5-93c4-bf91191c0fb7","order_by":1,"name":"Xiaoyan Yu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5klEQVRIiWNgGAWjYJCCA2CSvYeBGcJPIFYLzxkStECARA6RWgxu5Bge+FFxWN5c8u2xz4U7DjPws+cYMPzcgU9LWsLBnjOHDXfOzkuePfPMYQbJnjcGjL1n8GlJPnCAt+0w44bbOcbMQAbIXgNmxjZ8WhIbDv5tO2y/4eYZiBZ7wlqSDxwGqkzccIMHaosEAS2SZ54lHJY5k5684QzQYTPb0nkkzjwrONiLRwvf8Rzjj28qrG03HAc6rLDNWo6/PXnjg594tCgcAFPNcAEeEHEAtwYGBvkGMFWHT80oGAWjYBSMdAAAGONXo217kcMAAAAASUVORK5CYII=","orcid":"","institution":"Harbin Normal University","correspondingAuthor":true,"prefix":"","firstName":"Xiaoyan","middleName":"","lastName":"Yu","suffix":""},{"id":375738483,"identity":"1b9489b9-3409-4007-a7c9-cc24ad5bc8ac","order_by":2,"name":"Xianwei Rong","email":"","orcid":"","institution":"Harbin Normal University","correspondingAuthor":false,"prefix":"","firstName":"Xianwei","middleName":"","lastName":"Rong","suffix":""},{"id":375738484,"identity":"2bb44f8e-f7e5-4b1d-825d-ec4c321c2618","order_by":3,"name":"Xiaozhou Wang","email":"","orcid":"","institution":"Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Xiaozhou","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2024-11-01 01:38:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5369748/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5369748/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":70441496,"identity":"7a29315b-1657-48ff-93df-55c66fa7d9fb","added_by":"auto","created_at":"2024-12-03 08:02:17","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1191639,"visible":true,"origin":"","legend":"","description":"","filename":"manuscriptforScientificReports.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5369748/v1_covered_7f2c029d-0938-4f46-a9c7-a895a142ef78.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"AFF-LightNet: Attentional Feature Fusion Based Lightweight Network for Ship 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":"Ship detection, Deep learning, Attentional feature fusion, Lightweight","lastPublishedDoi":"10.21203/rs.3.rs-5369748/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5369748/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Efficient mobile detection equipment plays a vital role in ensuring maritime safety, and accurate ship identification is crucial for maritime traffic. Recently, advanced learning-based methods boost the accuracy of ship detection, but face challenges on mobile devices due to size and computation. Thus, we propose a lightweight ship detection network based on feature fusion, called AFF-LightNet. We introduce iterative attentional feature fusion (IAFF) into the proposed neck network, improving the efficiency of feature fusion by introducing a multi-scale channel attention module. Also, Conv is replaced by DCNv2 in the backbone network to further improve the detection accuracy of the proposed network. DCNv2 enhances the spatial sampling position in convolution and Rol pooling by introducing offsets. Moreover, a lightweight convolution GhostConv was introduced into the head network to reduce the number of parameters and computation cost. Last, SIOU was leveraged to improve the convergence speed of the model. We conduct extensive experiments on the publicly available dataset SeaShips and compare it with existing methods. The experimental results show that compared with the standard YOLOv8n, the improved network has an average accuracy of 98.8%, an increase of 0.4%, a reduction of 1.9 G in computational complexity, and a reduction of 0.19 M in parameter count.","manuscriptTitle":"AFF-LightNet: Attentional Feature Fusion Based Lightweight Network for Ship Detection","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-11-15 09:31:33","doi":"10.21203/rs.3.rs-5369748/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":"fac211e1-b2ca-4591-b88f-5d0374f9f24a","owner":[],"postedDate":"November 15th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":40003361,"name":"Physical sciences/Mathematics and computing/Computational science"},{"id":40003362,"name":"Physical sciences/Mathematics and computing/Computer science"}],"tags":[],"updatedAt":"2024-12-03T07:54:09+00:00","versionOfRecord":[],"versionCreatedAt":"2024-11-15 09:31:33","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5369748","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5369748","identity":"rs-5369748","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}