Sketch Recognition Using Mamba Model for Computer Vision Tasks

Sketch Recognition Using Mamba Model for Computer Vision Tasks | 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 Sketch Recognition Using Mamba Model for Computer Vision Tasks Viola H. Cheeseman, Cai Bo, Prasun Chakrabarti, Jian Luo, Kamran Azi This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6365924/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Sketch recognition involves classifying and retrieving hand-drawn sketches. Traditional deep learning models like CNNs, RNNs, and transformers often struggle due to unbalanced datasets and poor generalization across sketch styles and categories. These limitations hinder the development of effective systems. To address these challenges, we propose Mamba, a novel deep learning framework for sketch classification and retrieval. Mamba integrates CNNs for feature extraction, RNNs for capturing temporal dependencies, and a dedicated Mamba module that enhances visual attention mechanisms and feature activation mapping. Our dynamic refinement of sketch representations improves generalization and adaptability. We then trained on large-scale datasets such as QuickDraw, TU-Berlin, and SketchyScene. Mamba outperforms existing methods in terms of recognition accuracy, robustness, and interpretability. Our evaluations demonstrate that Mamba not only improves classification precision but also provides valuable insights into feature attribution. This framework is a promising approach for real-world sketch recognition applications, highlighting the importance of structured feature representation learning and attention mechanisms to enhance reliability, ease of use, and performance in sketch-based computer vision. Biological sciences/Computational biology and bioinformatics Biological sciences/Neuroscience Physical sciences/Engineering Physical sciences/Mathematics and computing/Scientific data Sketch Recognition Deep Learning Computer Vision Mamba Model Sketch Classification Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted 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-6365924","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":450524856,"identity":"8ac6bbc8-67c7-4c6f-b882-ccb7ab8c70b6","order_by":0,"name":"Viola H. Cheeseman","email":"","orcid":"","institution":"Wuhan University","correspondingAuthor":false,"prefix":"","firstName":"Viola","middleName":"H.","lastName":"Cheeseman","suffix":""},{"id":450524857,"identity":"23fef1f0-28c2-4fbc-931a-14f7a7458463","order_by":1,"name":"Cai Bo","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAArklEQVRIiWNgGAWjYFACxjaGDwwHQCwD4rUwziBRCwMbMw9JWvjbD7c9tm27k9jA3rxNgqHmDmEtEmcS241z254lNvAcK5NgOPaMsBYDhsQ26dxthxMbJHLMJBgbDhOhhf9hm7QlSIv8G2K1SABtYQTbwkOkFokbD9sNe/8dNm7jSSu2SDhGhBb+/vRnD36cOSzbz354440PNURogQM2EJFAgoZRMApGwSgYBXgAACC1OwtdyztBAAAAAElFTkSuQmCC","orcid":"","institution":"Wuhan University","correspondingAuthor":true,"prefix":"","firstName":"Cai","middleName":"","lastName":"Bo","suffix":""},{"id":450524858,"identity":"19868b6f-5cfe-448a-8b08-dabaf4d10e92","order_by":2,"name":"Prasun Chakrabarti","email":"","orcid":"","institution":"Wuhan University","correspondingAuthor":false,"prefix":"","firstName":"Prasun","middleName":"","lastName":"Chakrabarti","suffix":""},{"id":450524859,"identity":"f8b5b7d9-a3c8-495c-abab-67c07052ba1b","order_by":3,"name":"Jian Luo","email":"","orcid":"","institution":"Wuhan University","correspondingAuthor":false,"prefix":"","firstName":"Jian","middleName":"","lastName":"Luo","suffix":""},{"id":450524860,"identity":"9c39cda6-d756-4a85-9574-cfd20956fdfc","order_by":4,"name":"Kamran Azi","email":"","orcid":"","institution":"Wuhan University","correspondingAuthor":false,"prefix":"","firstName":"Kamran","middleName":"","lastName":"Azi","suffix":""}],"badges":[],"createdAt":"2025-04-03 05:08:13","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6365924/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6365924/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":91616764,"identity":"cbe98a0b-d668-4939-a4b2-8acf3543fd9c","added_by":"auto","created_at":"2025-09-18 10:40:28","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":886014,"visible":true,"origin":"","legend":"","description":"","filename":"ManuscritptSketchRecognitionUsingMambaModel.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6365924/v1_covered_697af3cc-238c-4ff2-a433-279b57aca339.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Sketch Recognition Using Mamba Model for Computer Vision Tasks","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"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":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Sketch Recognition, Deep Learning, Computer Vision, Mamba Model, Sketch Classification","lastPublishedDoi":"10.21203/rs.3.rs-6365924/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6365924/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Sketch recognition involves classifying and retrieving hand-drawn sketches. Traditional deep learning models like CNNs, RNNs, and transformers often struggle due to unbalanced datasets and poor generalization across sketch styles and categories. These limitations hinder the development of effective systems. To address these challenges, we propose Mamba, a novel deep learning framework for sketch classification and retrieval. Mamba integrates CNNs for feature extraction, RNNs for capturing temporal dependencies, and a dedicated Mamba module that enhances visual attention mechanisms and feature activation mapping. Our dynamic refinement of sketch representations improves generalization and adaptability. We then trained on large-scale datasets such as QuickDraw, TU-Berlin, and SketchyScene. Mamba outperforms existing methods in terms of recognition accuracy, robustness, and interpretability. Our evaluations demonstrate that Mamba not only improves classification precision but also provides valuable insights into feature attribution. This framework is a promising approach for real-world sketch recognition applications, highlighting the importance of structured feature representation learning and attention mechanisms to enhance reliability, ease of use, and performance in sketch-based computer vision.","manuscriptTitle":"Sketch Recognition Using Mamba Model for Computer Vision Tasks","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-06 07:13:31","doi":"10.21203/rs.3.rs-6365924/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"5ffe1443-3838-42f8-b1b5-2e1db6e7d268","owner":[],"postedDate":"May 6th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":47937917,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":47937918,"name":"Biological sciences/Neuroscience"},{"id":47937919,"name":"Physical sciences/Engineering"},{"id":47937920,"name":"Physical sciences/Mathematics and computing/Scientific data"}],"tags":[],"updatedAt":"2025-09-18T10:39:38+00:00","versionOfRecord":[],"versionCreatedAt":"2025-05-06 07:13:31","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6365924","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6365924","identity":"rs-6365924","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}