A Semi-supervised Object Detection Learning Method under Queue Smoothing Pseudo-label Supervising and Embedding Consistency Constraint

A Semi-supervised Object Detection Learning Method under Queue Smoothing Pseudo-label Supervising and Embedding Consistency Constraint | 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 Semi-supervised Object Detection Learning Method under Queue Smoothing Pseudo-label Supervising and Embedding Consistency Constraint Xibin Jia, Sanlong You, Luo Wang, Senhui Jia, Hao Jia This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4879981/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 7 You are reading this latest preprint version Abstract Semi-supervised object detection is an effective solution to balance the manual annotation cost and model performance in practical application. However, two major types of semi-supervised learning approaches based on the pseudo-labeling supervising and the consistency constrained self-supervising exist some limitation with the low confidence of pseudo-label and the suboptimal feature learning for specific-task respectively. To overcome the above limitation, we proposes an improved semi-supervised object detection learning method under queue smoothing pseudo-label supervising and embedding consistency constraint learning method. In detail, taking the teacher-student framework as the base model, two paralleled transforming modules i.e. a classification head and a embedding projection layer are constructed after the feature encoder. With the different data augmentation exerting on inputs at the teacher and the student module respectively, a pair of class-vector and embedding are obtained simultaneously for each proposal. Subsequently, under the smoothness assumption of class prediction probability within the same cluster, a class-vector is updating weighting with smooth constraints calculating in the embedding similarity between memorized neighboring samples and corresponding pseudo-label is corrected with the increasing confidence then. Furthermore, dual constraints are constructed based on pseudo-label supervising and consistency between the class-vector and embedding matrix together with a few label data for guiding the semi-supervised object detection learning. The experiments on the MS-COCO and PASCAL VOC datasets demonstrate that the proposed method outperforms the baseline method and several mainstream semi-supervised learning methods with the highest mAP. semi-supervised object detection queue smoothing pseudo-labels consistency constraint data augmentation Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 18 Aug, 2024 Reviewers agreed at journal 18 Aug, 2024 Reviewers agreed at journal 18 Aug, 2024 Reviewers invited by journal 18 Aug, 2024 Editor assigned by journal 09 Aug, 2024 Submission checks completed at journal 09 Aug, 2024 First submitted to journal 08 Aug, 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-4879981","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":347901452,"identity":"112e3996-4d65-4821-bd86-e801f7e65343","order_by":0,"name":"Xibin Jia","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3ElEQVRIiWNgGAWjYBACxmYgkdggwcAvwZAAFmggWovkDKCWA8RoYYCZbHADyCBKC3M78zOJhzss8oxvNzyT/sBgI7vhAPOzB/gdxmZskHhGotjszoE0iQMMacYbDrCZGxDwi+GDxDaJxG03EkBaDiduOMDDJoFfC/uHAyAtm2eAtfwnRgsPxJYNEmAtB4jSUgzyS+KMOweSLc4YJBvPPMxmhleLYf/xbZI/d9Ql9s/uSbxRUWEn23e8+Rl+LQ1wJk8CMHaANDM+9UAgj2CyHyCgdhSMglEwCkYqAACDXk26qZXkmwAAAABJRU5ErkJggg==","orcid":"","institution":"Beijing University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Xibin","middleName":"","lastName":"Jia","suffix":""},{"id":347901453,"identity":"9d153832-4ba7-440f-89ea-ffef79122284","order_by":1,"name":"Sanlong You","email":"","orcid":"","institution":"Beijing University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Sanlong","middleName":"","lastName":"You","suffix":""},{"id":347901454,"identity":"5035846c-2023-4c03-9667-f8b7e79177fb","order_by":2,"name":"Luo Wang","email":"","orcid":"","institution":"Beijing University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Luo","middleName":"","lastName":"Wang","suffix":""},{"id":347901456,"identity":"9bb93e43-6fe2-45bc-820b-3271d39fb0cb","order_by":3,"name":"Senhui Jia","email":"","orcid":"","institution":"Beijing University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Senhui","middleName":"","lastName":"Jia","suffix":""},{"id":347901459,"identity":"fb03e89f-1917-4c71-acec-4c51d30c6cca","order_by":4,"name":"Hao Jia","email":"","orcid":"","institution":"Beijing University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Hao","middleName":"","lastName":"Jia","suffix":""}],"badges":[],"createdAt":"2024-08-08 09:44:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4879981/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4879981/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":64027236,"identity":"a0284e80-c553-4368-91f7-63adef69581d","added_by":"auto","created_at":"2024-09-05 08:04:02","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":328925,"visible":true,"origin":"","legend":"","description":"","filename":"NPLOD.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4879981/v1_covered_e1c1e1ed-28f0-4d3b-88d3-21244db94a95.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Semi-supervised Object Detection Learning Method under Queue Smoothing Pseudo-label Supervising and Embedding Consistency Constraint","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":"neural-processing-letters","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"nepl","sideBox":"Learn more about [Neural Processing Letters](http://link.springer.com/journal/11063)","snPcode":"11063","submissionUrl":"https://submission.nature.com/new-submission/11063/3","title":"Neural Processing Letters","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"semi-supervised object detection, queue smoothing, pseudo-labels, consistency constraint, data augmentation","lastPublishedDoi":"10.21203/rs.3.rs-4879981/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4879981/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eSemi-supervised object detection is an effective solution to balance the manual annotation cost and model performance in practical application. However, two major types of semi-supervised learning approaches based on the pseudo-labeling supervising and the consistency constrained self-supervising exist some limitation with the low confidence of pseudo-label and the suboptimal feature learning for specific-task respectively. To overcome the above limitation, we proposes an improved semi-supervised object detection learning method under queue smoothing pseudo-label supervising and embedding consistency constraint learning method. In detail, taking the teacher-student framework as the base model, two paralleled transforming modules \u003cem\u003ei.e.\u003c/em\u003e a classification head and a embedding projection layer are constructed after the feature encoder. With the different data augmentation exerting on inputs at the teacher and the student module respectively, a pair of class-vector and embedding are obtained simultaneously for each proposal. Subsequently, under the smoothness assumption of class prediction probability within the same cluster, a class-vector is updating weighting with smooth constraints calculating in the embedding similarity between memorized neighboring samples and corresponding pseudo-label is corrected with the increasing confidence then. Furthermore, dual constraints are constructed based on pseudo-label supervising and consistency between the class-vector and embedding matrix together with a few label data for guiding the semi-supervised object detection learning. The experiments on the MS-COCO and PASCAL VOC datasets demonstrate that the proposed method outperforms the baseline method and several mainstream semi-supervised learning methods with the highest mAP.\u003c/p\u003e","manuscriptTitle":"A Semi-supervised Object Detection Learning Method under Queue Smoothing Pseudo-label Supervising and Embedding Consistency Constraint","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-09-05 07:55:56","doi":"10.21203/rs.3.rs-4879981/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2024-08-19T02:59:47+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"7318611003354969794825691898804433958","date":"2024-08-19T02:22:09+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"118617984311642509134708142134685685225","date":"2024-08-18T09:12:44+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-08-18T08:36:29+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-08-09T08:11:13+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-08-09T08:09:16+00:00","index":"","fulltext":""},{"type":"submitted","content":"Neural Processing Letters","date":"2024-08-08T09:42:01+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"neural-processing-letters","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"nepl","sideBox":"Learn more about [Neural Processing Letters](http://link.springer.com/journal/11063)","snPcode":"11063","submissionUrl":"https://submission.nature.com/new-submission/11063/3","title":"Neural Processing Letters","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"37dfd093-a890-4cbb-81c7-1d0eeb4aca61","owner":[],"postedDate":"September 5th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-03-31T11:53:46+00:00","versionOfRecord":[],"versionCreatedAt":"2024-09-05 07:55:56","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4879981","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4879981","identity":"rs-4879981","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}