Lightweight NAS Super-Resolution model

Lightweight NAS Super-Resolution model | 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 Lightweight NAS Super-Resolution model Junyan Xie, Jiu Liang, Yu Zhang, Mingliang Han, Jincheng Wan, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4128456/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 This paper proposes a lightweight image super-resolution reconstruction algorithm (Lightweight NAS Super-Resolution model, LNSR) based on neural network architecture search. The search space of the algorithm is divided into Cell level and Network level. The design of the Cell-level search space is based on the RFDB structure, focusing on searching for combinations of lightweight operators, aiming to build a more lightweight and efficient structure. The Network-level search space focuses on searching the feature connections between Cells, aiming to find the information flow that is most beneficial to improve performance. In order to reduce the time of network architecture search, this paper extends the search strategy of MiLeNAS. At the same time, this paper uses a new type of loss function, which comprehensively considers image distortion, high-frequency detail reconstruction, and model size to promote the model to search for a lightweight and high-performance network structure. The experimental results show that LNSR only needs to spend about 2 days on a 2080 Ti to search for the optimal network structure, and the hardware resources and time consumed are much less than that of FALSR-B. In terms of network scale and performance, LNSR surpasses the artificial design and NAS-based SOTA lightweight method with a lower amount of parameters and calculation. super-resolution lightweight involution self-attention 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-4128456","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":281593776,"identity":"6564dc0e-122a-4773-a18c-e0379c6af0b0","order_by":0,"name":"Junyan Xie","email":"","orcid":"","institution":"Shaanxi Normal University","correspondingAuthor":false,"prefix":"","firstName":"Junyan","middleName":"","lastName":"Xie","suffix":""},{"id":281593777,"identity":"387db938-2b0d-44ba-a503-2165bb2efbbd","order_by":1,"name":"Jiu Liang","email":"","orcid":"","institution":"Shaanxi Normal University","correspondingAuthor":false,"prefix":"","firstName":"Jiu","middleName":"","lastName":"Liang","suffix":""},{"id":281593778,"identity":"4f472fa0-0854-4bbc-81c6-478ccb1d352a","order_by":2,"name":"Yu Zhang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6ElEQVRIiWNgGAWjYDACCQglx8/eABU5QKQWY8kemFJitSRuuJFApBb52c3PHn5tO2zMcPP5s8eFbQxyfDcSGD8X4NHCOOeYubFs22E5xtk55sYz24AuvJHALD0DjxZmiQQzaUmgLczSOWzSvG1gF7Ix8+DRwiaR/g2kJbFN8vgzkJZ6glp4JHLMJD8CtfRIMJiBtCQYENIiIZFTJs1wLt1YgifHTJrnnIThzDMPm6XxaZGfkb5N8keZtZz9caDDeMps5PmOJx/8jE8LCDDzsiFsBWLGBgIagEp+/CGoZhSMglEwCkYyAABx20YmujcWvwAAAABJRU5ErkJggg==","orcid":"","institution":"Shaanxi Normal University","correspondingAuthor":true,"prefix":"","firstName":"Yu","middleName":"","lastName":"Zhang","suffix":""},{"id":281593779,"identity":"fb604297-3bbb-407a-b2bd-020a48538036","order_by":3,"name":"Mingliang Han","email":"","orcid":"","institution":"Shaanxi Normal University","correspondingAuthor":false,"prefix":"","firstName":"Mingliang","middleName":"","lastName":"Han","suffix":""},{"id":281593780,"identity":"74e3c4ff-dacc-4921-b6b8-fe04267c024a","order_by":4,"name":"Jincheng Wan","email":"","orcid":"","institution":"Shaanxi Normal University","correspondingAuthor":false,"prefix":"","firstName":"Jincheng","middleName":"","lastName":"Wan","suffix":""},{"id":281593781,"identity":"6f042afa-d1e4-4437-b3f8-98a163f033ea","order_by":5,"name":"Shui Yu","email":"","orcid":"","institution":"Shaanxi Normal University","correspondingAuthor":false,"prefix":"","firstName":"Shui","middleName":"","lastName":"Yu","suffix":""}],"badges":[],"createdAt":"2024-03-19 08:15:39","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4128456/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4128456/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":54863150,"identity":"d02f7e73-467d-4a08-8398-d17ced95a399","added_by":"auto","created_at":"2024-04-17 20:22:26","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2351062,"visible":true,"origin":"","legend":"","description":"","filename":"LightweightImageSuperResolutionNetworkusinginvolution.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4128456/v1_covered_a52e670f-9aab-44c4-a3fb-c6be01ce2f92.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Lightweight NAS Super-Resolution model","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":"super-resolution, lightweight, involution, self-attention","lastPublishedDoi":"10.21203/rs.3.rs-4128456/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4128456/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"This paper proposes a lightweight image super-resolution reconstruction algorithm (Lightweight NAS Super-Resolution model, LNSR) based on neural network architecture search. The search space of the algorithm is divided into Cell level and Network level. The design of the Cell-level search space is based on the RFDB structure, focusing on searching for combinations of lightweight operators, aiming to build a more lightweight and efficient structure. The Network-level search space focuses on searching the feature connections between Cells, aiming to find the information flow that is most beneficial to improve performance. In order to reduce the time of network architecture search, this paper extends the search strategy of MiLeNAS. At the same time, this paper uses a new type of loss function, which comprehensively considers image distortion, high-frequency detail reconstruction, and model size to promote the model to search for a lightweight and high-performance network structure. The experimental results show that LNSR only needs to spend about 2 days on a 2080 Ti to search for the optimal network structure, and the hardware resources and time consumed are much less than that of FALSR-B. In terms of network scale and performance, LNSR surpasses the artificial design and NAS-based SOTA lightweight method with a lower amount of parameters and calculation.","manuscriptTitle":"Lightweight NAS Super-Resolution model","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-03-22 04:51:31","doi":"10.21203/rs.3.rs-4128456/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":"ad5d4b71-52ca-4e54-bff3-bb1c260eee8b","owner":[],"postedDate":"March 22nd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-04-17T20:14:18+00:00","versionOfRecord":[],"versionCreatedAt":"2024-03-22 04:51:31","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4128456","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4128456","identity":"rs-4128456","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}