NCANet: Integrating Normalized Channel Attention for Enhanced Lightweight Image Classification

NCANet: Integrating Normalized Channel Attention for Enhanced Lightweight Image Classification | 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 NCANet: Integrating Normalized Channel Attention for Enhanced Lightweight Image Classification Qian Chentao, Bailin Liu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4008005/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 Deep convolutional neural networks (CNN) have demonstrated remarkable success in various applications.However, deploying these models on mobile or embedded devices is challenging due to constraints such as limited memory, computational resources, and low classification accuracy.We propose a novel design, NCANet (Normalized Channel Attention Network),an enhancedversion of MobileNetV3-large, to address challenges in feature representation within lightweight neural networks.First, the normalized channel attention mechanism is added to adjust the image-feature channel weights so as to improve the recognition accuracy of the model.Second, the MetaACON activation function is introduced, replacing the ReLU activation function to further enhance performance.Third, to minimize computational costs and the number of parameters, we utilize asymmetric 1×5 and 5×1 convolutions to replace the traditional 5×5 convolution. The experimental results on CIFAR-10, CIFAR-100 and ImageNet datasets achieve the highest accuracy 93.24%, 80.12% and 77.9%, respectively.This demonstrates that NCANet exhibits greater efficiency compared to lightweight models and significantly outperforms state-of-the-art networks with lower complexity. image classification MobileNet V3 lightweight attention asymmetric convolutions Full Text Cite Share Download PDF Status: Under Review Version 1 posted Reviewers agreed at journal 16 Aug, 2024 Reviewers invited by journal 16 Aug, 2024 Editor invited by journal 15 Aug, 2024 First submitted to journal 03 Mar, 2024 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-4008005","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":341188299,"identity":"4f5cb3d7-3fae-4ae8-8b95-34b9ee4c83c7","order_by":0,"name":"Qian Chentao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAuElEQVRIiWNgGAWjYJCCgx9+SMiBGAeI1MDM+Fiyx8KYJC3MBjxsFYkNRDuK7/j5YxISPBLp88MOPzzAUGMTTVCL5JlkNokCC4ncjbfTDA4wHEvLJWidwQ1mNpAtuRtnJxgcYGw4TKQWHjaJdMPZ6R+I1gLyvkSCvHQOkbYA/WIIDGQJww3SOQUHEojxC9/xgw+AUVknLz87ffOHDzU2hLXAo88AxEggqBxZizxh00fBKBgFo2CkAgBchUDBLKtIzAAAAABJRU5ErkJggg==","orcid":"","institution":"Xi'an Technological University","correspondingAuthor":true,"prefix":"","firstName":"Qian","middleName":"","lastName":"Chentao","suffix":""},{"id":341188300,"identity":"adbbff5a-ca50-41c8-960f-78b1080aab27","order_by":1,"name":"Bailin Liu","email":"","orcid":"","institution":"Xi'an Technological University","correspondingAuthor":false,"prefix":"","firstName":"Bailin","middleName":"","lastName":"Liu","suffix":""}],"badges":[],"createdAt":"2024-03-03 08:49:19","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4008005/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4008005/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":64479022,"identity":"79f14c64-3c28-487e-b482-695fd2f2c69d","added_by":"auto","created_at":"2024-09-13 16:06:05","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":975707,"visible":true,"origin":"","legend":"","description":"","filename":"SOCOD2401187.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4008005/v1_covered_55717485-5e84-421e-b086-2c8bb8f4709e.pdf"}],"financialInterests":"","formattedTitle":"NCANet: Integrating Normalized Channel Attention for Enhanced Lightweight Image Classification","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"soft-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"soco","sideBox":"Learn more about [Soft Computing](https://www.springer.com/journal/500)","snPcode":"500","submissionUrl":"https://submission.nature.com/new-submission/500/3","title":"Soft Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"image classification, MobileNet V3, lightweight, attention, asymmetric convolutions","lastPublishedDoi":"10.21203/rs.3.rs-4008005/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4008005/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eDeep convolutional neural networks (CNN) have demonstrated remarkable success in various applications.However, deploying these models on mobile or embedded devices is challenging due to constraints such as limited memory, computational resources, and low classification accuracy.We propose a novel design, NCANet (Normalized Channel Attention Network),an enhancedversion of MobileNetV3-large, to address challenges in feature representation within lightweight neural networks.First, the normalized channel attention mechanism is added to adjust the image-feature channel weights so as to improve the recognition accuracy of the model.Second, the MetaACON activation function is introduced, replacing the ReLU activation function to further enhance performance.Third, to minimize computational costs and the number of parameters, we utilize asymmetric 1\u0026times;5 and 5\u0026times;1 convolutions to replace the traditional 5\u0026times;5 convolution. The experimental results on CIFAR-10, CIFAR-100 and ImageNet datasets achieve the highest accuracy 93.24%, 80.12% and 77.9%, respectively.This demonstrates that NCANet exhibits greater efficiency compared to lightweight models and significantly outperforms state-of-the-art networks with lower complexity.\u003c/p\u003e","manuscriptTitle":"NCANet: Integrating Normalized Channel Attention for Enhanced Lightweight Image Classification","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-09-13 15:57:58","doi":"10.21203/rs.3.rs-4008005/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"","date":"2024-08-16T15:57:32+00:00","index":0,"fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-08-16T14:53:30+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"Soft Computing","date":"2024-08-15T16:30:11+00:00","index":"","fulltext":""},{"type":"submitted","content":"Soft Computing","date":"2024-03-03T08:50:50+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"soft-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"soco","sideBox":"Learn more about [Soft Computing](https://www.springer.com/journal/500)","snPcode":"500","submissionUrl":"https://submission.nature.com/new-submission/500/3","title":"Soft Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"6a90428a-4332-4a35-93ea-0f09a42068f7","owner":[],"postedDate":"September 13th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-06-30T12:19:25+00:00","versionOfRecord":[],"versionCreatedAt":"2024-09-13 15:57:58","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4008005","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4008005","identity":"rs-4008005","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}