Balancing Accuracy and Efficiency: A Comparative Study of CNN Models on Versatile Image Datasets

Balancing Accuracy and Efficiency: A Comparative Study of CNN Models on Versatile Image Datasets | 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 Balancing Accuracy and Efficiency: A Comparative Study of CNN Models on Versatile Image Datasets Imran Zahid, Naima Hasan This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8736765/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 In this work, we explore a varieity of Convolutional Neural Network architectures, including both existing architectures and proposing some variations, and evaluate their performance across publicly available image datasets focused on real world use cases in Bangladesh. At first, we examine different choices in the design of our architecture, such as convolutional depth, pooling strategies, bottleneck layers, normalization and classifier head configuration in order to propose a compact and stable architecture for image classification. Based on our findings, we propose a compact CNN built around a shallow convolutional structure with max pooling layers and a global average pooling layer at the end. Then, we compare the proposed architecture against VGG16 and ResNet18, both pre-trained and with transfer learning, in order to evaluate its performance. Our results conclude that the proposed architecture can achieve competitive performance in various datasets with different dataset sizes while offering an advantage in model size and training efficiency. Convolutional Neural Networks Compact CNN Architectures Image Classification Full Text Additional Declarations The authors declare no competing interests. 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-8736765","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":582789056,"identity":"496b8dc5-a621-49aa-b59f-a59d694d8454","order_by":0,"name":"Imran Zahid","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6UlEQVRIiWNgGAWjYBACNiidwMDA2MzAUAFkMjM3kKLlDEgLI34tMJAAUsvA2AZiE9DCJ3b24ecChro8BrHDzQYf59VG87cDtfyo2IbbYdLpxtIzGNiKGaQTmxNnbjueO+MwYwNjz5nbeLSkMUjzMPAkNgC1HObddiy3AaiFmbENrxbm3zwMElAtc47lzidCCxvQFgOwlmTehprcDcRoseYxSEhsA2oxnHHsQO5GoJaD+PwiPzuN+TZPRV1iv3T6Y4kPNXW5884fPvjgRwVuLRBgAI/Tw2DyAAH1KKCOFMWjYBSMglEwQgAAkyhPoWHLZqkAAAAASUVORK5CYII=","orcid":"","institution":"University of Dhaka","correspondingAuthor":true,"prefix":"","firstName":"Imran","middleName":"","lastName":"Zahid","suffix":""},{"id":582789057,"identity":"2bc3eea2-edaa-4ed0-b0c4-552eb55ec314","order_by":1,"name":"Naima Hasan","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8ElEQVRIie3PsQ4BMRjA8TZN3OKYDXgFYhAJ7lXaGCw8gcEl4rMcMzF4BRYx3qWDRWLtpRaLTXI2hMTVZnDOJtFfmn7L909ThDTtJ2FbnZDhukE4Ekb8JMm8sUpIzIeUEk+q8SkpG7w/v6zqVnpqU169LvMpgnBwar1PKg4Df7hpsPHOc3l7JItAEMlMlu+TgstAmEAoEpTytiNxmCSIGZVs9+DfoWvlBS3wiiOtz4lgIE3geK4SdJYsRrIHmYU1W4gW9Ya2bADBvei/bJsH/wgdKyeaPDjfZG026HnBKSJ5heF523H3lds3y5qmaf/iAZT4XVkB/BXQAAAAAElFTkSuQmCC","orcid":"","institution":"University of Dhaka","correspondingAuthor":true,"prefix":"","firstName":"Naima","middleName":"","lastName":"Hasan","suffix":""}],"badges":[],"createdAt":"2026-01-30 04:05:05","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-8736765/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8736765/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":101648792,"identity":"11145712-6262-4393-be54-e393008e4db4","added_by":"auto","created_at":"2026-02-02 08:59:47","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2566791,"visible":true,"origin":"","legend":"","description":"","filename":"BalancingAccuracyandEfficiencyAComparativeStudyofCNNModelsonVersatileImageDatasets.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8736765/v1_covered_e630388d-80d3-499c-b6a0-18e2763332f5.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eBalancing Accuracy and Efficiency: A Comparative Study of CNN Models on Versatile Image Datasets\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"University of Dhaka","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":"Convolutional Neural Networks, Compact CNN Architectures, Image Classification","lastPublishedDoi":"10.21203/rs.3.rs-8736765/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8736765/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eIn this work, we explore a varieity of Convolutional Neural Network architectures, including both existing architectures and proposing some variations, and evaluate their performance across publicly available image datasets focused on real world use cases in Bangladesh. At first, we examine different choices in the design of our architecture, such as convolutional depth, pooling strategies, bottleneck layers, normalization and classifier head configuration in order to propose a compact and stable architecture for image classification. Based on our findings, we propose a compact CNN built around a shallow convolutional structure with max pooling layers and a global average pooling layer at the end. Then, we compare the proposed architecture against VGG16 and ResNet18, both pre-trained and with transfer learning, in order to evaluate its performance. Our results conclude that the proposed architecture can achieve competitive performance in various datasets with different dataset sizes while offering an advantage in model size and training efficiency.\u003c/p\u003e","manuscriptTitle":"Balancing Accuracy and Efficiency: A Comparative Study of CNN Models on Versatile Image Datasets","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-02 08:58:00","doi":"10.21203/rs.3.rs-8736765/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":"ecb4abfb-3bfb-4132-9947-b1998e66bcec","owner":[],"postedDate":"February 2nd, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-02-02T08:58:00+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-02 08:58:00","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8736765","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8736765","identity":"rs-8736765","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}