PCPE-YOLO: A Lightweight Object Detection Framework with Dynamic Reconfigurable Backbone for Enhanced Small Object Recognition

PCPE-YOLO: A Lightweight Object Detection Framework with Dynamic Reconfigurable Backbone for Enhanced Small Object Recognition | 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 PCPE-YOLO: A Lightweight Object Detection Framework with Dynamic Reconfigurable Backbone for Enhanced Small Object Recognition Weijia Chen, Jiaming Liu, Tong Liu, Yaoming Zhuang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6800061/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 16 Aug, 2025 Read the published version in Scientific Reports → Version 1 posted 13 You are reading this latest preprint version Abstract In the domain of object detection, small object detection remains a pressing challenge, as existing approaches often suffer from limited accuracy, high model complexity, and difficulty meeting lightweight deployment requirements. In this paper, we propose PCPE-YOLO, a novel object detection algorithm, specifically designed to address these difficulties. First, we put forward a dynamic, reconfigurable C2f backbone and refine it to create the C2f_PIG module. This module uses a parameter-aware mechanism to adapt its bottleneck structures to different network depths and widths, reducing parameters while maintaining performance. Next, we introduce a Context Anchor Attention mechanism that boosts the model’s focus on the contexts of small objects, thereby improving detection accuracy. In addition, we add a small object detection layer to enhance the model’s localization capability for small objects. Finally, we integrate an Efficient Up-Convolution Block to sharpen decoder feature maps, enhancing small object recall with minimal computational overhead. Experiments on VisDrone2019, KITTI, and NWPU VHR-10 datasets show that PCPE-YOLO significantly outperforms both the baseline and other state-of-the-art methods in precision, recall, mean average precision, and parameters, achieving the best precision among all compared approaches. On VisDrone2019 in particular, it achieves improvements of 3.8% in precision, 5.6% in recall, 6.2% in mAP50, and 5% in F1 score, effectively combining lightweight design with high small object detection performance and providing a more efficient and reliable solution for small object detection in real-world applications. Physical sciences/Mathematics and computing Physical sciences/Mathematics and computing/Computer science YOLOv8 Object Detection Small Object Lightweight Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 16 Aug, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 08 Jul, 2025 Reviews received at journal 05 Jul, 2025 Reviews received at journal 01 Jul, 2025 Reviewers agreed at journal 01 Jul, 2025 Reviewers agreed at journal 01 Jul, 2025 Reviews received at journal 10 Jun, 2025 Reviewers agreed at journal 10 Jun, 2025 Reviewers agreed at journal 09 Jun, 2025 Reviewers invited by journal 09 Jun, 2025 Editor assigned by journal 09 Jun, 2025 Editor invited by journal 09 Jun, 2025 Submission checks completed at journal 06 Jun, 2025 First submitted to journal 06 Jun, 2025 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-6800061","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":469524256,"identity":"f48db278-0b42-4f08-aa6b-60c7e86c9542","order_by":0,"name":"Weijia Chen","email":"","orcid":"","institution":"Northeastern University","correspondingAuthor":false,"prefix":"","firstName":"Weijia","middleName":"","lastName":"Chen","suffix":""},{"id":469524257,"identity":"c6e635e5-ddce-47bd-8bc4-4ff9d8fd7095","order_by":1,"name":"Jiaming Liu","email":"","orcid":"","institution":"Northeastern University","correspondingAuthor":false,"prefix":"","firstName":"Jiaming","middleName":"","lastName":"Liu","suffix":""},{"id":469524258,"identity":"004994a2-d091-4989-b824-1547dba423e6","order_by":2,"name":"Tong Liu","email":"","orcid":"","institution":"Northeastern University","correspondingAuthor":false,"prefix":"","firstName":"Tong","middleName":"","lastName":"Liu","suffix":""},{"id":469524259,"identity":"baba56d4-aadb-4f0c-ab3b-6d2275625823","order_by":3,"name":"Yaoming Zhuang","email":"data:image/png;base64,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","orcid":"","institution":"Northeastern University","correspondingAuthor":true,"prefix":"","firstName":"Yaoming","middleName":"","lastName":"Zhuang","suffix":""}],"badges":[],"createdAt":"2025-06-02 08:08:36","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6800061/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6800061/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-15975-w","type":"published","date":"2025-08-16T15:57:38+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":89310705,"identity":"862ac799-fcf4-41bf-bdcc-3f4b777596b7","added_by":"auto","created_at":"2025-08-18 16:09:59","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1086550,"visible":true,"origin":"","legend":"","description":"","filename":"PCPEYOLO.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6800061/v1_covered_ad3cbe8e-5777-4a6f-a88f-66e9732105cd.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"PCPE-YOLO: A Lightweight Object Detection Framework with Dynamic Reconfigurable Backbone for Enhanced Small Object Recognition","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":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"YOLOv8, Object Detection, Small Object, Lightweight","lastPublishedDoi":"10.21203/rs.3.rs-6800061/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6800061/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"In the domain of object detection, small object detection remains a pressing challenge, as existing approaches often suffer from limited accuracy, high model complexity, and difficulty meeting lightweight deployment requirements. In this paper, we propose PCPE-YOLO, a novel object detection algorithm, specifically designed to address these difficulties. First, we put forward a dynamic, reconfigurable C2f backbone and refine it to create the C2f_PIG module. This module uses a parameter-aware mechanism to adapt its bottleneck structures to different network depths and widths, reducing parameters while maintaining performance. Next, we introduce a Context Anchor Attention mechanism that boosts the model’s focus on the contexts of small objects, thereby improving detection accuracy. In addition, we add a small object detection layer to enhance the model’s localization capability for small objects. Finally, we integrate an Efficient Up-Convolution Block to sharpen decoder feature maps, enhancing small object recall with minimal computational overhead. Experiments on VisDrone2019, KITTI, and NWPU VHR-10 datasets show that PCPE-YOLO significantly outperforms both the baseline and other state-of-the-art methods in precision, recall, mean average precision, and parameters, achieving the best precision among all compared approaches. On VisDrone2019 in particular, it achieves improvements of 3.8% in precision, 5.6% in recall, 6.2% in mAP50, and 5% in F1 score, effectively combining lightweight design with high small object detection performance and providing a more efficient and reliable solution for small object detection in real-world applications.","manuscriptTitle":"PCPE-YOLO: A Lightweight Object Detection Framework with Dynamic Reconfigurable Backbone for Enhanced Small Object Recognition","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-11 09:18:52","doi":"10.21203/rs.3.rs-6800061/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-07-08T05:49:13+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-07-05T05:18:20+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-07-02T03:37:11+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"290514293062872453161483803064600981555","date":"2025-07-02T02:18:55+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"67754028324624434276778824302499385390","date":"2025-07-01T11:33:09+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-11T03:02:12+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"59556436594138175692209729173153386822","date":"2025-06-11T02:09:02+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"269336253477916403817894815182197945777","date":"2025-06-10T03:27:31+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-06-10T03:12:32+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-06-10T03:09:28+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-06-09T14:38:38+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-06-06T07:14:10+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-06-06T07:10:08+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"8a1e97dc-7144-4d05-b72b-5af9661001ae","owner":[],"postedDate":"June 11th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":49852360,"name":"Physical sciences/Mathematics and computing"},{"id":49852361,"name":"Physical sciences/Mathematics and computing/Computer science"}],"tags":[],"updatedAt":"2025-08-18T16:07:37+00:00","versionOfRecord":{"articleIdentity":"rs-6800061","link":"https://doi.org/10.1038/s41598-025-15975-w","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-08-16 15:57:38","publishedOnDateReadable":"August 16th, 2025"},"versionCreatedAt":"2025-06-11 09:18:52","video":"","vorDoi":"10.1038/s41598-025-15975-w","vorDoiUrl":"https://doi.org/10.1038/s41598-025-15975-w","workflowStages":[]},"version":"v1","identity":"rs-6800061","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6800061","identity":"rs-6800061","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}