Frequency-Aware Elastic Prototype Boundary Learning for Long-Tailed Scene Graph Generation

Frequency-Aware Elastic Prototype Boundary Learning for Long-Tailed Scene Graph Generation | 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 Frequency-Aware Elastic Prototype Boundary Learning for Long-Tailed Scene Graph Generation Binghao Wang, Xueying Sun, Hanzhu Dai, Yuqi Shi, Qiang Zhang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9516264/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 4 You are reading this latest preprint version Abstract Scene graph generation (SGG) addresses the task of detecting objects in an image and predicting the relationships among them. Although prototype-based methods have recently achieved clear progress on long-tailed SGG, fine-grained low-frequency predicates remain difficult to recognize because their relation features often exhibit larger intra-class variation and more dispersed distributions, making them easily confused with semantically similar high-frequency coarse-grained predicates under a unified prototype-matching rule. To alleviate this issue, we propose a frequency-aware elastic prototype boundary learning framework, termed SGE-Net. Under fixed relation prototypes, the framework learns relation-category-specific boundary scales through explicit frequency compensation and frequency-adaptive virtual sampling, so that relation prediction can exploit not only prototype-center matching but also category-dependent decision-boundary information. During inference, we further introduce elastic boundary-aware distance calibration, enabling the boundary information learned during training to better distinguish relation categories that are easily confused under prototype matching. In addition, we combine visual and semantic features with dynamic gating to provide more reliable relation features for the above boundary learning. Experiments and analyses on Visual Genome and Open Images V6 demonstrate that the proposed method achieves consistent gains in both long-tailed relation prediction and overall evaluation metrics. scene graph generation long-tailed relation prediction prototype boundary learning visual-semantic fusion elastic boundary-aware distance calibration Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers invited by journal 28 Apr, 2026 Editor assigned by journal 24 Apr, 2026 Submission checks completed at journal 24 Apr, 2026 First submitted to journal 24 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-9516264","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":633654027,"identity":"c6b8b70d-df9b-4ebe-8485-e6d4410f7f1e","order_by":0,"name":"Binghao Wang","email":"","orcid":"","institution":"Jiangsu University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Binghao","middleName":"","lastName":"Wang","suffix":""},{"id":633654028,"identity":"7e425dc9-0601-4741-8b3a-50e66bd10fad","order_by":1,"name":"Xueying Sun","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+ElEQVRIiWNgGAWjYBADHgYG5gMGEHYC0VrYEoBaDIjXAtIFUk6EFvkZucekeSoOy5jzr/lQzPPnDwM/e44Bw88duLUY3MhLNuY5c5jHcsbbDca8bQYMkj1vDBh7z+DRIpFj+Ji37TCPwY2zQC0NBkBDcgyYGdvwOSzH4DDvP5CWMw+Mef4YMNgT0sJwA2RLA1DL+R4GYx42A5C9+LUYnHljbDjnWDrQFjYDw7ltxjwSZ54VHOzF57D2HDOJNzXW9gbnDz8zePNHTo6/PXnjg5/4HAYBzQwMEglsoEjhAXEPENTAwFDHwMB/gPkBESpHwSgYBaNgBAIAPkBNY1/SHJcAAAAASUVORK5CYII=","orcid":"","institution":"Jiangsu University of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Xueying","middleName":"","lastName":"Sun","suffix":""},{"id":633654029,"identity":"509c83d9-ea2f-4cd6-a0a0-3e06cb73d7d0","order_by":2,"name":"Hanzhu Dai","email":"","orcid":"","institution":"Jiangsu University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Hanzhu","middleName":"","lastName":"Dai","suffix":""},{"id":633654030,"identity":"b1404453-3a0a-4dff-bfdf-12435d6652fb","order_by":3,"name":"Yuqi Shi","email":"","orcid":"","institution":"Jiangsu University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Yuqi","middleName":"","lastName":"Shi","suffix":""},{"id":633654031,"identity":"6ef1c510-d56d-4e40-be85-11e1285ce1e2","order_by":4,"name":"Qiang Zhang","email":"","orcid":"","institution":"Jiangsu University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Qiang","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2026-04-24 10:54:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9516264/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9516264/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108977041,"identity":"2d533f83-ce83-4431-8822-ba8ee15f03e2","added_by":"auto","created_at":"2026-05-11 11:30:06","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2411990,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9516264/v1_covered_ff9af37e-b82b-48d4-a175-af3847ab20a6.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Frequency-Aware Elastic Prototype Boundary Learning for Long-Tailed Scene Graph Generation","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-king-saud-university-computer-and-information-sciences","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Journal of King Saud University Computer and Information Sciences](https://link.springer.com/journal/44443)","snPcode":"44443","submissionUrl":"https://submission.springernature.com/new-submission/44443/3","title":"Journal of King Saud University Computer and Information Sciences","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Open","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"scene graph generation, long-tailed relation prediction, prototype boundary learning, visual-semantic fusion, elastic boundary-aware distance calibration","lastPublishedDoi":"10.21203/rs.3.rs-9516264/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9516264/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eScene graph generation (SGG) addresses the task of detecting objects in an image and predicting the relationships among them. Although prototype-based methods have recently achieved clear progress on long-tailed SGG, fine-grained low-frequency predicates remain difficult to recognize because their relation features often exhibit larger intra-class variation and more dispersed distributions, making them easily confused with semantically similar high-frequency coarse-grained predicates under a unified prototype-matching rule. To alleviate this issue, we propose a frequency-aware elastic prototype boundary learning framework, termed SGE-Net. Under fixed relation prototypes, the framework learns relation-category-specific boundary scales through explicit frequency compensation and frequency-adaptive virtual sampling, so that relation prediction can exploit not only prototype-center matching but also category-dependent decision-boundary information. During inference, we further introduce elastic boundary-aware distance calibration, enabling the boundary information learned during training to better distinguish relation categories that are easily confused under prototype matching. In addition, we combine visual and semantic features with dynamic gating to provide more reliable relation features for the above boundary learning. Experiments and analyses on Visual Genome and Open Images V6 demonstrate that the proposed method achieves consistent gains in both long-tailed relation prediction and overall evaluation metrics.\u003c/p\u003e","manuscriptTitle":"Frequency-Aware Elastic Prototype Boundary Learning for Long-Tailed Scene Graph Generation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-07 05:28:02","doi":"10.21203/rs.3.rs-9516264/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewersInvited","content":"","date":"2026-04-28T15:09:36+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-25T03:47:36+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-25T03:47:05+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of King Saud University Computer and Information Sciences","date":"2026-04-24T10:48:20+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"journal-of-king-saud-university-computer-and-information-sciences","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Journal of King Saud University Computer and Information Sciences](https://link.springer.com/journal/44443)","snPcode":"44443","submissionUrl":"https://submission.springernature.com/new-submission/44443/3","title":"Journal of King Saud University Computer and Information Sciences","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Open","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"910d5460-5ccb-45bb-b998-ac1d4145d0cc","owner":[],"postedDate":"May 7th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-07T05:28:02+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-07 05:28:02","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9516264","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9516264","identity":"rs-9516264","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}