Toward Sustainable Deep Learning: Comparative Analysis and Optimization of Semantic Segmentation Models

Toward Sustainable Deep Learning: Comparative Analysis and Optimization of Semantic Segmentation Models | 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 Toward Sustainable Deep Learning: Comparative Analysis and Optimization of Semantic Segmentation Models Rima Hasna Yamouni, Faten Mosrati, Rim Trabelsi, Adnane Cabani, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7014730/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 begin{abstract}SSemantic segmentation models have become foundational in vision-based applications, yet their environmental impact remains insufficiently explored. In this study, we conduct a comprehensive evaluation of state-of-the-art deep learning architectures for semantic segmentation, jointly analyzing segmentation accuracy, energy consumption, and carbon emissions. We further benchmark the reliability of existing energy tracking tools, identifying the most accurate for measuring training and inference efficiency. Our results reveal a trade-off between performance and environmental cost, with top-performing models often incurring significant energy overhead. To address this, we propose and evaluate targeted optimization strategies, including weight pruning and backbone freezing, that significantly reduce energy usage while preserving segmentation accuracy. Our findings establish a framework for sustainable model development and highlight the importance of integrating environmental efficiency into the design of next-generation computer vision systems.\end{abstract} Green deep learning Semantic segmentation 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-7014730","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":482491818,"identity":"849c698e-c804-4109-882b-b9447312f550","order_by":0,"name":"Rima Hasna Yamouni","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABAklEQVRIiWNgGAWjYDACZjBCAmzsDSRr4TkAY+HVhQwkEvBrMW/nTvxcUFOXx9/AY/jpRsXhPD7J58+kC2psohnkew9g0yJzmHez9Ixjh4slDvAYS+ecOVzMJp1jBhRJy21g40vApkWCmXeDNA/bgcSGAzwG0rlthxPbpHPYpHkbDgO18Bjg0LL5N8+/usT5QFt+g7VIHn9GSMs2ad425sQNB3jMILZIMJgR1GLN23c4ceNhtjLrnDPpiW08OcbWIL+0seVg18J/dvNtnm91ifOON2++nVNhnTi//fjD28AQy+1nPoNVCwIwcyAUgGMKT0zCAPsDVC2jYBSMglEwCqAAALPXWEmObahjAAAAAElFTkSuQmCC","orcid":"","institution":"University of Carthage, SUP'COM","correspondingAuthor":true,"prefix":"","firstName":"Rima","middleName":"Hasna","lastName":"Yamouni","suffix":""},{"id":482491822,"identity":"a4e52559-4831-4e51-9b47-1be25f323ce6","order_by":1,"name":"Faten Mosrati","email":"","orcid":"","institution":"University of Carthage, SUP'COM","correspondingAuthor":false,"prefix":"","firstName":"Faten","middleName":"","lastName":"Mosrati","suffix":""},{"id":482491823,"identity":"d597e4a8-0398-4546-b7c8-59f8c29938ab","order_by":2,"name":"Rim Trabelsi","email":"","orcid":"","institution":"University of Gabès","correspondingAuthor":false,"prefix":"","firstName":"Rim","middleName":"","lastName":"Trabelsi","suffix":""},{"id":482491824,"identity":"74771865-eb81-4b37-bec7-3cb2e40c2c20","order_by":3,"name":"Adnane Cabani","email":"","orcid":"","institution":"Université de Rouen Normandie, ESIGELEC","correspondingAuthor":false,"prefix":"","firstName":"Adnane","middleName":"","lastName":"Cabani","suffix":""},{"id":482491826,"identity":"fa4ab97f-c744-4862-b730-4e0287822a38","order_by":4,"name":"Fatma Abdelkefi","email":"","orcid":"","institution":"University of Carthage, SUP'COM","correspondingAuthor":false,"prefix":"","firstName":"Fatma","middleName":"","lastName":"Abdelkefi","suffix":""}],"badges":[],"createdAt":"2025-07-01 00:53:12","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-7014730/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7014730/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":88439930,"identity":"6b3e7f36-3593-4f18-97a1-4def20bf9447","added_by":"auto","created_at":"2025-08-06 12:32:08","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":503858,"visible":true,"origin":"","legend":"","description":"","filename":"TowardSustainableDeepLearningComparativeAnalysisandOptimizationofSemanticSegmentationModels.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7014730/v1_covered_c4dada99-b367-4c77-abbd-8eaa574f3cc0.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Toward Sustainable Deep Learning: Comparative Analysis and Optimization of Semantic Segmentation Models","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":"Green deep learning, Semantic segmentation","lastPublishedDoi":"10.21203/rs.3.rs-7014730/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7014730/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003ebegin{abstract}SSemantic segmentation models have become foundational in vision-based applications, yet their environmental impact remains insufficiently explored. In this study, we conduct a comprehensive evaluation of state-of-the-art deep learning architectures for semantic segmentation, jointly analyzing segmentation accuracy, energy consumption, and carbon emissions. We further benchmark the reliability of existing energy tracking tools, identifying the most accurate for measuring training and inference efficiency. Our results reveal a trade-off between performance and environmental cost, with top-performing models often incurring significant energy overhead. To address this, we propose and evaluate targeted optimization strategies, including weight pruning and backbone freezing, that significantly reduce energy usage while preserving segmentation accuracy. Our findings establish a framework for sustainable model development and highlight the importance of integrating environmental efficiency into the design of next-generation computer vision systems.\\end{abstract}\u003c/p\u003e","manuscriptTitle":"Toward Sustainable Deep Learning: Comparative Analysis and Optimization of Semantic Segmentation Models","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-10 04:13:17","doi":"10.21203/rs.3.rs-7014730/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":"9b0594c0-b90c-454f-8dd1-dc60c25155e6","owner":[],"postedDate":"July 10th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-08-06T12:24:00+00:00","versionOfRecord":[],"versionCreatedAt":"2025-07-10 04:13:17","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7014730","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7014730","identity":"rs-7014730","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}