CFDN: Cross-scale Feature Distillation Network for Lightweight Single Image Super-Resolution

CFDN: Cross-scale Feature Distillation Network for Lightweight Single Image Super-Resolution | 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 CFDN: Cross-scale Feature Distillation Network for Lightweight Single Image Super-Resolution Zihan Mu, Ge Zhu, Jinping Tang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4399143/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 26 Nov, 2024 Read the published version in Multimedia Systems → Version 1 posted 12 You are reading this latest preprint version Abstract Information distillation play an important role in lightweight Single image super-resolution (SISR) by retaining and extracting hierarchical features step-by-step. This allows the network to possess a deep and compact structure, enabling it to achieve lightweight while maintaining good performance. However, the features prematurely retained by the distilled branches cannot be fully utilized, making it difficult for the model to effectively learn the multi-scale semantics and details. To solve above problems, we propose a Cross-scale Feature Distillation Network (CFDN), which consists of the basic module called Cross-scale Feature Distillation Block (CFDB) and sub-module called Multiple Receptive field Aggregation Block (MRAB). Different from the previous distillation structures that lost insight of extracting multi-scale information due to the use of simple distillation units, the proposed CFDB module designed with a novel distillation strategy can capture multi-scale information, thereby providing the diversity of features to the retained and purified branches. In each retained/distilled branch of CFDB, the sub-module MRAB equipped with pixel attention and dilated convolutions is designed to capture multi-scale semantics and details by enlarging receptive field processively. Experiments on five datasets show that the proposed network achieves superior performance over the other state-of-the-art lightweight SR methods. Single image super-resolution Lightweight network Cross-scale feature distillation Multiple receptive field Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 26 Nov, 2024 Read the published version in Multimedia Systems → Version 1 posted Editorial decision: Revision requested 28 Jun, 2024 Reviews received at journal 25 Jun, 2024 Reviews received at journal 16 Jun, 2024 Reviews received at journal 11 Jun, 2024 Reviewers agreed at journal 11 Jun, 2024 Reviewers agreed at journal 04 Jun, 2024 Reviewers agreed at journal 03 Jun, 2024 Reviewers agreed at journal 03 Jun, 2024 Reviewers invited by journal 02 Jun, 2024 Editor assigned by journal 02 Jun, 2024 Submission checks completed at journal 10 May, 2024 First submitted to journal 10 May, 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-4399143","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":314204130,"identity":"8570e52c-7d1c-4981-bf54-fd5f4b69a5d2","order_by":0,"name":"Zihan Mu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA80lEQVRIie3RMYoCMRSA4RcC2sSxfYPgXCGDsCgIXiWDhc0uWMlUmkWYbTyAVl5hjpBB0Gawnk7EA7hgsYUWJlrYZaYUNj+vCu+DBwFwud6wZn2enW4c2wCMKDRPqoT4i+2Qs7jb0QSqEV58fiDL40gaAlUIKMHRT3C0lg2legm0vUKQy9giiNQmTPArVZ5QfgIdvxC0tbQQakxkCDBuSJQWokaZhdSMyfRhgXySWSlh2nzLHAWoJxG8jKA2FGIM040muMdwlR/nLRsZHM5/V+DTIPhZhCec9ANvN8wuNvKK6kEwn0lkJfCI/Fbfdblcrn/UHexrSr6GZQ0/AAAAAElFTkSuQmCC","orcid":"","institution":"Heilongjiang University","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Zihan","middleName":"","lastName":"Mu","suffix":""},{"id":314204131,"identity":"02fa9f6c-39c5-4e22-bb04-334a999f6690","order_by":1,"name":"Ge Zhu","email":"","orcid":"","institution":"Heilongjiang University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Ge","middleName":"","lastName":"Zhu","suffix":""},{"id":314204132,"identity":"529ba955-6c66-4a3e-8ae9-a8e0e5880c50","order_by":2,"name":"Jinping Tang","email":"","orcid":"","institution":"Heilongjiang University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Jinping","middleName":"","lastName":"Tang","suffix":""}],"badges":[],"createdAt":"2024-05-10 08:07:08","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4399143/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4399143/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00530-024-01488-5","type":"published","date":"2024-11-26T15:58:12+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":70382825,"identity":"03303675-047e-4609-bb8b-8e77baf10532","added_by":"auto","created_at":"2024-12-02 16:32:15","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":990710,"visible":true,"origin":"","legend":"","description":"","filename":"CFDN.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4399143/v1_covered_ecb2f364-db76-4180-924b-c485652e1600.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"CFDN: Cross-scale Feature Distillation Network for Lightweight Single Image Super-Resolution","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":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"multimedia-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mmsj","sideBox":"Learn more about [Multimedia Systems](http://link.springer.com/journal/530)","snPcode":"530","submissionUrl":"https://submission.nature.com/new-submission/530/3","title":"Multimedia Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Single image super-resolution, Lightweight network, Cross-scale feature distillation, Multiple receptive field","lastPublishedDoi":"10.21203/rs.3.rs-4399143/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4399143/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Information distillation play an important role in lightweight Single image super-resolution (SISR) by retaining and extracting hierarchical features step-by-step. This allows the network to possess a deep and compact structure, enabling it to achieve lightweight while maintaining good performance. However, the features prematurely retained by the distilled branches cannot be fully utilized, making it difficult for the model to effectively learn the multi-scale semantics and details. To solve above problems, we propose a Cross-scale Feature Distillation Network (CFDN), which consists of the basic module called Cross-scale Feature Distillation Block (CFDB) and sub-module called Multiple Receptive field Aggregation Block (MRAB). Different from the previous distillation structures that lost insight of extracting multi-scale information due to the use of simple distillation units, the proposed CFDB module designed with a novel distillation strategy can capture multi-scale information, thereby providing the diversity of features to the retained and purified branches. In each retained/distilled branch of CFDB, the sub-module MRAB equipped with pixel attention and dilated convolutions is designed to capture multi-scale semantics and details by enlarging receptive field processively. Experiments on five datasets show that the proposed network achieves superior performance over the other state-of-the-art lightweight SR methods.","manuscriptTitle":"CFDN: Cross-scale Feature Distillation Network for Lightweight Single Image Super-Resolution","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-06-14 04:40:36","doi":"10.21203/rs.3.rs-4399143/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-06-28T07:21:05+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-06-25T05:05:59+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-06-16T21:38:26+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-06-12T02:56:05+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"3949124362792840639823050273646713970","date":"2024-06-11T11:39:04+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"21136260519919716934555273113645332399","date":"2024-06-04T22:30:37+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"310044462763928999170397749397969939004","date":"2024-06-03T09:18:12+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"235357789253081651015116470528535160990","date":"2024-06-03T06:48:16+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-06-03T03:09:47+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-06-02T15:16:59+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-05-10T13:14:42+00:00","index":"","fulltext":""},{"type":"submitted","content":"Multimedia Systems","date":"2024-05-10T08:05:49+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"multimedia-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mmsj","sideBox":"Learn more about [Multimedia Systems](http://link.springer.com/journal/530)","snPcode":"530","submissionUrl":"https://submission.nature.com/new-submission/530/3","title":"Multimedia Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"cf97f146-44a2-4be3-a6e7-2bd6761bc8a8","owner":[],"postedDate":"June 14th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2024-12-02T16:04:54+00:00","versionOfRecord":{"articleIdentity":"rs-4399143","link":"https://doi.org/10.1007/s00530-024-01488-5","journal":{"identity":"multimedia-systems","isVorOnly":false,"title":"Multimedia Systems"},"publishedOn":"2024-11-26 15:58:12","publishedOnDateReadable":"November 26th, 2024"},"versionCreatedAt":"2024-06-14 04:40:36","video":"","vorDoi":"10.1007/s00530-024-01488-5","vorDoiUrl":"https://doi.org/10.1007/s00530-024-01488-5","workflowStages":[]},"version":"v1","identity":"rs-4399143","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4399143","identity":"rs-4399143","version":["v1"]},"buildId":"WrCJVZZCHTDjtuVLN7oU0","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}