MoEMASeg: An Enhanced DeepLab V3 Combining MobileNet V2 and EMA

MoEMASeg: An Enhanced DeepLab V3 Combining MobileNet V2 and EMA | 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 MoEMASeg: An Enhanced DeepLab V3 Combining MobileNet V2 and EMA Weili Chen, Xin Guo, Lingui Li This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6237306/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 Computer vision has become ubiquitous, with artificial intelligence continuously evolving, and deep learning emerging as one of the primary approaches in image processing. While the current DeepLabV3+ based image segmentation algorithm achieves high accuracy, its computational complexity, resource consumption, and intricate feature maps result in substantial processing time, making it unsuitable for real-time applications. In this paper, we propose an improved DeepLabV3 image segmentation algorithm (MoEMASeg). The proposed method employs the lightweight MobileNetV2 as the backbone feature extraction network and incorporates an EMA (Efficient Multi-Scale Attention), which effectively reduces the model’s parameters and computational overhead. Additionally, the EMA module enhances image semantic segmentation performance by facilitating better integration of multi-scale features. We adopt a combined loss function incorporating cross-entropy and Dice coefficient to further improve segmentation accuracy. Experimental validation is conducted on the PASCAL-VOC dataset, evaluating the model across multiple dimensions including accuracy, parameter count, and inference time. The experimental results demonstrate that our improved method significantly reduces the parameter count compared to the original DeepLabV3, while achieving an MIoU of 87.15%. This represents a substantial reduction in algorithmic complexity and execution time while maintaining segmentation quality. The proposed model exhibits robust performance in object contour detection and provides a novel technical solution for real-time lightweight image segmentation applications. Physical sciences/Engineering/Electrical and electronic engineering Physical sciences/Engineering/Mechanical engineering Physical sciences/Mathematics and computing/Computational science Physical sciences/Mathematics and computing/Computer science Physical sciences/Mathematics and computing Physical sciences/Mathematics and computing/Software 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-6237306","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":443106506,"identity":"11cc7602-9c5c-486c-b498-02bd5b44c005","order_by":0,"name":"Weili Chen","email":"","orcid":"","institution":"Guangdong Communication Polytechnic","correspondingAuthor":false,"prefix":"","firstName":"Weili","middleName":"","lastName":"Chen","suffix":""},{"id":443106507,"identity":"de2e78b3-8895-4fba-8ce9-e1b8c1d1e1ae","order_by":1,"name":"Xin Guo","email":"","orcid":"","institution":"Guangdong Communication Polytechnic","correspondingAuthor":false,"prefix":"","firstName":"Xin","middleName":"","lastName":"Guo","suffix":""},{"id":443106508,"identity":"aa594b41-7867-4c82-a784-955a57a9f451","order_by":2,"name":"Lingui Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA00lEQVRIiWNgGAWjYFCCBMMDDypsmO3bG4AcAwuitBgcSDiTxm7AcwCkRYJILYlth/kNJBJAPCK06LYnbwDacljaXPL51Q0/CiQY+Nu7E/BqMTvzrOBAQkW6seXsnLKbPUCHSZw5uwG/lhs5IL9YJzPczkm7wQPUYiCRS4SWxDbm+oabZ9Ju/iFBizOzwQ32Y7eJswXslzNpzJI9OWy3ZQwkeAj75XjyxgcfgFHJz3782c03f2zk+Nt78WtBAjwGYJJY5SDA/oAU1aNgFIyCUTCCAACAVlFjADrS2wAAAABJRU5ErkJggg==","orcid":"","institution":"Guangzhou College of Commerce","correspondingAuthor":true,"prefix":"","firstName":"Lingui","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2025-03-16 11:38:16","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6237306/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6237306/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":83129714,"identity":"305f44c0-9d8f-4375-814d-adb3e714c1f4","added_by":"auto","created_at":"2025-05-20 10:08:37","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4292622,"visible":true,"origin":"","legend":"","description":"","filename":"MoEMASegAnEnhancedDeepLabV3CombiningMobileNetV2andEMA3.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6237306/v1_covered_ae1011b9-c50d-4298-bb9f-963c0b169415.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003eMoEMASeg: An Enhanced DeepLab V3 Combining MobileNet V2 and EMA\u003c/p\u003e","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":"","lastPublishedDoi":"10.21203/rs.3.rs-6237306/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6237306/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eComputer vision has become ubiquitous, with artificial intelligence continuously evolving, and deep learning emerging as one of the primary approaches in image processing. While the current DeepLabV3+ based image segmentation algorithm achieves high accuracy, its computational complexity, resource consumption, and intricate feature maps result in substantial processing time, making it unsuitable for real-time applications. In this paper, we propose an improved DeepLabV3 image segmentation algorithm (MoEMASeg). The proposed method employs the lightweight MobileNetV2 as the backbone feature extraction network and incorporates an EMA (Efficient Multi-Scale Attention), which effectively reduces the model’s parameters and computational overhead. Additionally, the EMA module enhances image semantic segmentation performance by facilitating better integration of multi-scale features. We adopt a combined loss function incorporating cross-entropy and Dice coefficient to further improve segmentation accuracy. Experimental validation is conducted on the PASCAL-VOC dataset, evaluating the model across multiple dimensions including accuracy, parameter count, and inference time. The experimental results demonstrate that our improved method significantly reduces the parameter count compared to the original DeepLabV3, while achieving an MIoU of 87.15%. This represents a substantial reduction in algorithmic complexity and execution time while maintaining segmentation quality. The proposed model exhibits robust performance in object contour detection and provides a novel technical solution for real-time lightweight image segmentation applications.\u003c/p\u003e","manuscriptTitle":"MoEMASeg: An Enhanced DeepLab V3 Combining MobileNet V2 and EMA","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-23 15:34:24","doi":"10.21203/rs.3.rs-6237306/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":"105e05cf-f040-4b84-aafb-2214b3b16d18","owner":[],"postedDate":"April 23rd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":47581546,"name":"Physical sciences/Engineering/Electrical and electronic engineering"},{"id":47581547,"name":"Physical sciences/Engineering/Mechanical engineering"},{"id":47581548,"name":"Physical sciences/Mathematics and computing/Computational science"},{"id":47581549,"name":"Physical sciences/Mathematics and computing/Computer science"},{"id":47581550,"name":"Physical sciences/Mathematics and computing"},{"id":47581551,"name":"Physical sciences/Mathematics and computing/Software"}],"tags":[],"updatedAt":"2025-05-20T10:08:10+00:00","versionOfRecord":[],"versionCreatedAt":"2025-04-23 15:34:24","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6237306","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6237306","identity":"rs-6237306","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}