An Underwater Object Detection Method Integrating Multi-Dimensional Attention and Task Decoupling Mechanism

An Underwater Object Detection Method Integrating Multi-Dimensional Attention and Task Decoupling Mechanism | 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 An Underwater Object Detection Method Integrating Multi-Dimensional Attention and Task Decoupling Mechanism Feng Zou, Jiaqi Ma, Botong Zhou, Shuanglong Liu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9313874/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 12 You are reading this latest preprint version Abstract Underwater object detection is of significant practical importance for marine resource exploration, underwater robotic navigation, and marine ecological monitoring. However, underwater images are often severely degraded by light attenuation and scattering, suspended particulates, and complex background interference. These factors lead to low contrast, strong color distortion, and blurred object boundaries, which collectively pose substantial challenges to reliable object detection. To address these issues, this paper proposes an object detection framework specifically designed for underwater environments. First, we develop a dynamic image feature-fusion backbone module, termed DyC2F (Dynamic Lightweight Convolution to Fusion). By embedding dynamic convolution into a dual-path architecture, DyC2F enhances the modeling of local textures and weak boundary features while maintaining low computational complexity. Second, a three-dimensional attention fusion mechanism, referred to as TDAF(Three-Dimensional Attention Fusion), is introduced to adaptively enhance multi-scale underwater features across channel, scale, and spatial dimensions, thereby improving the detectability of low-contrast small objects. Finally, the detection head is further optimized by incorporating a dynamic activation function, a task-decoupled alignment module, and a quality focal loss, which effectively mitigates feature conflicts between classification and localization in complex underwater backgrounds and improves prediction stability. Experimental results on representative underwater datasets demonstrate that the proposed method consistently outperforms mainstream approaches in terms of detection accuracy, robustness, and small-object recognition. Moreover, the proposed framework achieves a processing speed of 188.7 frames per second (fps), satisfying real-time detection requirements in complex underwater scenarios. Object detection Underwater scenes Three-dimensional attention Task decoupling Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 12 May, 2026 Reviews received at journal 11 May, 2026 Reviews received at journal 28 Apr, 2026 Reviewers agreed at journal 28 Apr, 2026 Reviews received at journal 27 Apr, 2026 Reviewers agreed at journal 25 Apr, 2026 Reviewers agreed at journal 21 Apr, 2026 Reviewers agreed at journal 20 Apr, 2026 Reviewers invited by journal 20 Apr, 2026 Editor assigned by journal 09 Apr, 2026 Submission checks completed at journal 09 Apr, 2026 First submitted to journal 03 Apr, 2026 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-9313874","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":629622429,"identity":"8ebf1f20-ae11-4875-9521-1c199238baba","order_by":0,"name":"Feng Zou","email":"","orcid":"","institution":"Hunan Normal University","correspondingAuthor":false,"prefix":"","firstName":"Feng","middleName":"","lastName":"Zou","suffix":""},{"id":629622441,"identity":"0ad5073f-1458-4e83-98db-dafe2f27d234","order_by":1,"name":"Jiaqi Ma","email":"","orcid":"","institution":"Hunan Normal University","correspondingAuthor":false,"prefix":"","firstName":"Jiaqi","middleName":"","lastName":"Ma","suffix":""},{"id":629622443,"identity":"a440f7f1-9383-4628-a820-ecb15bb5be0b","order_by":2,"name":"Botong Zhou","email":"","orcid":"","institution":"Hunan Normal University","correspondingAuthor":false,"prefix":"","firstName":"Botong","middleName":"","lastName":"Zhou","suffix":""},{"id":629622445,"identity":"3afcd3bd-36f4-4787-acee-d9219fe4f363","order_by":3,"name":"Shuanglong Liu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABEElEQVRIiWNgGAWjYBACPmYgwdgAYjKDSJsEqAQzTi1sCC1gMo0ILXDFEPIwEVrYeQwYf+44LG/Ov7DxccGv83kGt3uPSTBUWCc2sJ89gN1hPAbMvGcOG+6c8bDZeGbf7WKDO+fSJBjOpCc28OQl4NTC2HaYccONg23SvD23EzfcyDGTAIokNkjwGODSwviz7bA9VMs5qJZ/+LUw8ALN3HC+sU2a58cBqJYGfFrYCg7ztqUnb7jB2GzM25CcOPNGjrFFwrF04zaeHKxa+PkPb3z4s83adsP5wwcf8/yxS+y7kWN440ONtWw/+xmsWkDgAJiUAAYPYxtUCBRUbLjUI+wD6fxDUNkoGAWjYBSMQAAAYglimyww4TsAAAAASUVORK5CYII=","orcid":"","institution":"Hunan Normal University","correspondingAuthor":true,"prefix":"","firstName":"Shuanglong","middleName":"","lastName":"Liu","suffix":""}],"badges":[],"createdAt":"2026-04-03 14:25:08","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9313874/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9313874/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107875830,"identity":"7f85a197-b842-489c-bc0b-0ac511b0798b","added_by":"auto","created_at":"2026-04-27 08:11:07","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":658290,"visible":true,"origin":"","legend":"","description":"","filename":"AnUnderwaterObjectDetectionMethodIntegratingMultiDimensionalAttentionandTaskDecouplingMechanism.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9313874/v1_covered_8c91340e-85d5-4485-b5de-36743f7ee6c3.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"An Underwater Object Detection Method Integrating Multi-Dimensional Attention and Task Decoupling Mechanism","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"journal-of-real-time-image-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"rtip","sideBox":"Learn more about [Journal of Real-Time Image Processing](http://link.springer.com/journal/11554)","snPcode":"11554","submissionUrl":"https://submission.nature.com/new-submission/11554/3","title":"Journal of Real-Time Image Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Object detection, Underwater scenes, Three-dimensional attention, Task decoupling","lastPublishedDoi":"10.21203/rs.3.rs-9313874/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9313874/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Underwater object detection is of significant practical importance for marine resource exploration, underwater robotic navigation, and marine ecological monitoring. However, underwater images are often severely degraded by light attenuation and scattering, suspended particulates, and complex background interference. These factors lead to low contrast, strong color distortion, and blurred object boundaries, which collectively pose substantial challenges to reliable object detection. To address these issues, this paper proposes an object detection framework specifically designed for underwater environments. First, we develop a dynamic image feature-fusion backbone module, termed DyC2F (Dynamic Lightweight Convolution to Fusion). By embedding dynamic convolution into a dual-path architecture, DyC2F enhances the modeling of local textures and weak boundary features while maintaining low computational complexity. Second, a three-dimensional attention fusion mechanism, referred to as TDAF(Three-Dimensional Attention Fusion), is introduced to adaptively enhance multi-scale underwater features across channel, scale, and spatial dimensions, thereby improving the detectability of low-contrast small objects. Finally, the detection head is further optimized by incorporating a dynamic activation function, a task-decoupled alignment module, and a quality focal loss, which effectively mitigates feature conflicts between classification and localization in complex underwater backgrounds and improves prediction stability. Experimental results on representative underwater datasets demonstrate that the proposed method consistently outperforms mainstream approaches in terms of detection accuracy, robustness, and small-object recognition. Moreover, the proposed framework achieves a processing speed of 188.7 frames per second (fps), satisfying real-time detection requirements in complex underwater scenarios.","manuscriptTitle":"An Underwater Object Detection Method Integrating Multi-Dimensional Attention and Task Decoupling Mechanism","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-27 07:52:54","doi":"10.21203/rs.3.rs-9313874/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-05-12T06:32:08+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-11T15:33:03+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-29T03:32:43+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"90469673537747654548020926356393946620","date":"2026-04-28T12:53:35+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-27T17:11:32+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"84227428429902111965043881622735209128","date":"2026-04-26T02:58:58+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"121483121511221541834416323981399325663","date":"2026-04-21T14:31:20+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"54571731335756117203387709039449870268","date":"2026-04-20T09:23:21+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-20T08:15:19+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-09T09:18:33+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-09T09:18:29+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of Real-Time Image Processing","date":"2026-04-03T14:19:02+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"journal-of-real-time-image-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"rtip","sideBox":"Learn more about [Journal of Real-Time Image Processing](http://link.springer.com/journal/11554)","snPcode":"11554","submissionUrl":"https://submission.nature.com/new-submission/11554/3","title":"Journal of Real-Time Image Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"554a241b-a92b-4c56-8a0d-b1bf3673a596","owner":[],"postedDate":"April 27th, 2026","published":true,"recentEditorialEvents":[{"type":"editorInvitedReview","content":"","date":"2026-05-12T06:32:08+00:00","index":19,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-11T15:33:03+00:00","index":18,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-04-27T07:52:55+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-27 07:52:54","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9313874","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9313874","identity":"rs-9313874","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}