A lightweight fine-grained recognition algorithm based on object detection

A lightweight fine-grained recognition algorithm based on 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 Research Article A lightweight fine-grained recognition algorithm based on object detection Weiyu Ren, Dongfan Shi, Yifan Chen, Liming Song, Qingsong Hu, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4690928/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 11 You are reading this latest preprint version Abstract In order to enhance the fine-grained recognition of fish species, this paper proposes a lightweight object detection model YOLOv8n-DFG. The model accurately identifies six deep-sea fish species including Flatfin sailfish, Striped marlin, Atlantic bluefin tuna, Bigeye tuna, Longtail tuna, and Yellowfin tuna, meeting the requirements for real-time detection and fishing monitoring. Firstly, by introducing FasterNetBlock and EMA attention mechanism into the YOLOv8 network structure to improve C2f and obtain the C2f-FE module, this model enhances feature extraction accuracy and operational efficiency. Subsequently, it combines BiFPN structure with C2f-FE module to construct a fast and lightweight neck network structure that achieves multi-scale feature fusion. Additionally, Dysample dynamic upsampling module is introduced along with porting of Adown downsampling module from YOLOv9 to optimize feature pyramid sampling method named as YOLOv8-FG. Finally using large-sized YOLOv8s-FG as teacher network and small-sized YOLOv8n-FG as student network based on CWD loss intermediate layer feature distillation method constructs the final model YOLOv8n-DFG. Experimental results on a dataset containing six morphologically similar fish species demonstrate the effectiveness of these improvements and distillation effects are significant. Compared to YOLOv8n, precision has increased by 7.8%, recall by 3.3%, mAP@50 by 5.6%, while FlOPs decreased by 42% with a reduction in model size of 58%. The results indicate that our proposed YOLOv8n-DFG demonstrates exceptional accuracy and real-time performance, effectively fulfilling the requirements for real-time fine-grained fish recognition. Fine-grained fish recognition YOLOv8 Lightweight models Feature distillation Real-time object detection Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 23 Jul, 2024 Reviews received at journal 22 Jul, 2024 Reviews received at journal 21 Jul, 2024 Reviewers agreed at journal 11 Jul, 2024 Reviewers agreed at journal 08 Jul, 2024 Reviewers agreed at journal 07 Jul, 2024 Reviewers agreed at journal 06 Jul, 2024 Reviewers invited by journal 05 Jul, 2024 Editor assigned by journal 05 Jul, 2024 Submission checks completed at journal 05 Jul, 2024 First submitted to journal 05 Jul, 2024 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-4690928","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":330581666,"identity":"7ae5629d-ca68-4ae0-a356-81786482f051","order_by":0,"name":"Weiyu Ren","email":"","orcid":"","institution":"Shanghai Ocean University","correspondingAuthor":false,"prefix":"","firstName":"Weiyu","middleName":"","lastName":"Ren","suffix":""},{"id":330581667,"identity":"b9888364-c55b-4b95-b44e-c3dead463565","order_by":1,"name":"Dongfan Shi","email":"","orcid":"","institution":"East China University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Dongfan","middleName":"","lastName":"Shi","suffix":""},{"id":330581668,"identity":"ba575226-0822-45f9-afbd-ef8464e56896","order_by":2,"name":"Yifan Chen","email":"","orcid":"","institution":"Shanghai Ocean University","correspondingAuthor":false,"prefix":"","firstName":"Yifan","middleName":"","lastName":"Chen","suffix":""},{"id":330581669,"identity":"0fc0b620-5e77-46cb-8d04-2f224eb9afaa","order_by":3,"name":"Liming Song","email":"","orcid":"","institution":"Shanghai Ocean University","correspondingAuthor":false,"prefix":"","firstName":"Liming","middleName":"","lastName":"Song","suffix":""},{"id":330581670,"identity":"64594897-6843-4be6-ac0d-c1f6423e6fd2","order_by":4,"name":"Qingsong Hu","email":"","orcid":"","institution":"Shanghai Ocean University","correspondingAuthor":false,"prefix":"","firstName":"Qingsong","middleName":"","lastName":"Hu","suffix":""},{"id":330581671,"identity":"afe1bf09-70ae-4b4b-ade4-68ef24177ad3","order_by":5,"name":"Meiling Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAxklEQVRIiWNgGAWjYDACdjBpw2AAptmI0cIMJtNI13KYBC26zTyGnwt+nbc3Z+8xYPhQdpiBf3YDfi1mh3mMpWf23U7c2XPGgHHGucMMEncOENLCu0Gat+d2gsGNHANm3jagCyUSCGrZ/Ju355w9WMtfIrVsk+b5cYBxA0gLI3Fa+L9Z8zYkJ244c6zgYM+5dB6JG4S0HG9Lvs3zx87e4Hjzxgc/yqzl+GcQ0AIGjG0Q+gAQ8xChHgT+EKluFIyCUTAKRiYAANJkQwWZHw3hAAAAAElFTkSuQmCC","orcid":"","institution":"Shanghai Ocean University","correspondingAuthor":true,"prefix":"","firstName":"Meiling","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2024-07-05 08:51:17","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4690928/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4690928/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":61381270,"identity":"5ef903a3-fd84-48cb-8dd2-11d13d65ea6d","added_by":"auto","created_at":"2024-07-30 05:48:32","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":719421,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4690928/v1_covered_d96c0acc-c3b3-4710-8813-b5e12e111c44.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A lightweight fine-grained recognition algorithm based on object detection","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"","identity":"aquaculture-international","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"10499","submissionUrl":"https://submission.nature.com/new-submission/10499/3","title":"Aquaculture International","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"","reportingPortfolio":"VoR Journals","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Fine-grained fish recognition, YOLOv8, Lightweight models, Feature distillation, Real-time object detection","lastPublishedDoi":"10.21203/rs.3.rs-4690928/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4690928/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eIn order to enhance the fine-grained recognition of fish species, this paper proposes a lightweight object detection model YOLOv8n-DFG. The model accurately identifies six deep-sea fish species including Flatfin sailfish, Striped marlin, Atlantic bluefin tuna, Bigeye tuna, Longtail tuna, and Yellowfin tuna, meeting the requirements for real-time detection and fishing monitoring. Firstly, by introducing FasterNetBlock and EMA attention mechanism into the YOLOv8 network structure to improve C2f and obtain the C2f-FE module, this model enhances feature extraction accuracy and operational efficiency. Subsequently, it combines BiFPN structure with C2f-FE module to construct a fast and lightweight neck network structure that achieves multi-scale feature fusion. Additionally, Dysample dynamic upsampling module is introduced along with porting of Adown downsampling module from YOLOv9 to optimize feature pyramid sampling method named as YOLOv8-FG. Finally using large-sized YOLOv8s-FG as teacher network and small-sized YOLOv8n-FG as student network based on CWD loss intermediate layer feature distillation method constructs the final model YOLOv8n-DFG. Experimental results on a dataset containing six morphologically similar fish species demonstrate the effectiveness of these improvements and distillation effects are significant. Compared to YOLOv8n, precision has increased by 7.8%, recall by 3.3%, mAP@50 by 5.6%, while FlOPs decreased by 42% with a reduction in model size of 58%. The results indicate that our proposed YOLOv8n-DFG demonstrates exceptional accuracy and real-time performance, effectively fulfilling the requirements for real-time fine-grained fish recognition.\u003c/p\u003e","manuscriptTitle":"A lightweight fine-grained recognition algorithm based on object detection","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-07-30 05:40:24","doi":"10.21203/rs.3.rs-4690928/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-07-23T08:09:34+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-07-22T15:27:54+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-07-21T17:31:08+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"150675482852272519282645409588260110531","date":"2024-07-11T07:38:13+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"117775780474136880383621947734391056569","date":"2024-07-08T08:37:22+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"322895909768613786986199172506692957475","date":"2024-07-08T02:46:00+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"232072762703047290384333852841997967788","date":"2024-07-06T07:16:46+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-07-06T01:32:42+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-07-05T18:18:27+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-07-05T10:08:17+00:00","index":"","fulltext":""},{"type":"submitted","content":"Aquaculture International","date":"2024-07-05T08:49:54+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"","identity":"aquaculture-international","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"10499","submissionUrl":"https://submission.nature.com/new-submission/10499/3","title":"Aquaculture International","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"","reportingPortfolio":"VoR Journals","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"df457f2e-1578-4c0b-b876-ed98d85f8b37","owner":[],"postedDate":"July 30th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2024-08-29T05:39:10+00:00","versionOfRecord":[],"versionCreatedAt":"2024-07-30 05:40:24","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4690928","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4690928","identity":"rs-4690928","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}