Garbage FusionNet: A deep learning framework combining ResNet and Vision Transformer for waste classification

Garbage FusionNet: A deep learning framework combining ResNet and Vision Transformer for waste 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 Article Garbage FusionNet: A deep learning framework combining ResNet and Vision Transformer for waste classification Zhaoqi Wang, Wenxue Zhou, Yanmei Li This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4708918/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 26 Dec, 2024 Read the published version in Electronics → Version 1 posted You are reading this latest preprint version Abstract As global attention to environmental protection and sustainable resource utilization continues to rise, waste classification has emerged as a crucial issue that urgently needs to be addressed in the context of social development. Proper waste sorting not only helps reduce environmental pollution but also significantly enhances resource recycling rates, playing a vital role in promoting green and sustainable development. Compared to traditional manual waste sorting methods, deep learning-based waste classification systems offer remarkable advantages. This paper proposes an innovative deep learning framework named Garbage FusionNet (GFN) to tackle the waste classification problem. GFN significantly improves the classification performance by combining the local feature extraction capabilities of ResNet with the global information capturing abilities of Vision Transformer (ViT). GFN outperforms existing benchmark models on a ten-category waste classification dataset comprising 23,642 images. Experimental results demonstrate that GFN achieves superior performance on key metrics such as accuracy, weighted precision, weighted recall, and weighted F1-score. Specifically, GFN achieves an accuracy of 96.54%, surpassing standalone ResNet50 and ViT models by 1.09 and 4.18 percentage points, respectively. GFN offers an efficient and reliable solution for waste classification, highlighting the potential of deep learning in environmental protection. Earth and environmental sciences/Environmental sciences Earth and environmental sciences/Environmental social sciences Waste Classification Deep Learning Attention Mechanism Convolutional Neural Network Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 26 Dec, 2024 Read the published version in Electronics → 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-4708918","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":334399785,"identity":"d0fbdf39-7b67-48ee-a224-03e15b5add70","order_by":0,"name":"Zhaoqi Wang","email":"","orcid":"","institution":"Lanzhou Jiaotong University","correspondingAuthor":false,"prefix":"","firstName":"Zhaoqi","middleName":"","lastName":"Wang","suffix":""},{"id":334399788,"identity":"6d4f838c-ae8a-441b-9589-c497afbc09a7","order_by":1,"name":"Wenxue Zhou","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA0klEQVRIiWNgGAWjYHACNiC24WFjbz5w4EMF8VrS5Ph5jiUenHGGeC2HjSVn+Bgf5m0hQr3BjfRnDz62MSduuMHz4QBvA4M8v9gBAlrOHEg3nNnGlrjhdu+GA5I7GAxnzk7Ar8XseMMxad42nsQNd85uOGB4hiHB4DYhLYcZ24BaJIAOy3lwILGNGC3Hm9mAWgyA3s9hOHCQGC32Z46xSc44lwAKZIODDWckCPtFckb6M4kPZf9BUfn4858KG3l+aQJa0IEEacpHwSgYBaNgFGAHACLcS6QasFqeAAAAAElFTkSuQmCC","orcid":"","institution":"Lanzhou Jiaotong University","correspondingAuthor":true,"prefix":"","firstName":"Wenxue","middleName":"","lastName":"Zhou","suffix":""},{"id":334399792,"identity":"f9709e85-003c-4761-9a55-51b9db8bbe78","order_by":2,"name":"Yanmei Li","email":"","orcid":"","institution":"Lanzhou Jiaotong University","correspondingAuthor":false,"prefix":"","firstName":"Yanmei","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2024-07-09 03:51:26","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4708918/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4708918/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.3390/electronics14010075","type":"published","date":"2024-12-27T00:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":72715728,"identity":"900399da-d2a4-4e1a-b131-967d1c65a682","added_by":"auto","created_at":"2024-12-31 17:12:29","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":848857,"visible":true,"origin":"","legend":"","description":"","filename":"GarbageFusionNetAdeeplearningframeworkcombiningResNetandVisionTransformerforwasteclassification.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4708918/v1_covered_164fb29f-49a6-4fa0-9619-a4b0b8f1788e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Garbage FusionNet: A deep learning framework combining ResNet and Vision Transformer for waste 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":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":"Waste Classification, Deep Learning, Attention Mechanism, Convolutional Neural Network","lastPublishedDoi":"10.21203/rs.3.rs-4708918/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4708918/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"As global attention to environmental protection and sustainable resource utilization continues to rise, waste classification has emerged as a crucial issue that urgently needs to be addressed in the context of social development. Proper waste sorting not only helps reduce environmental pollution but also significantly enhances resource recycling rates, playing a vital role in promoting green and sustainable development. Compared to traditional manual waste sorting methods, deep learning-based waste classification systems offer remarkable advantages. This paper proposes an innovative deep learning framework named Garbage FusionNet (GFN) to tackle the waste classification problem. GFN significantly improves the classification performance by combining the local feature extraction capabilities of ResNet with the global information capturing abilities of Vision Transformer (ViT). GFN outperforms existing benchmark models on a ten-category waste classification dataset comprising 23,642 images. Experimental results demonstrate that GFN achieves superior performance on key metrics such as accuracy, weighted precision, weighted recall, and weighted F1-score. Specifically, GFN achieves an accuracy of 96.54%, surpassing standalone ResNet50 and ViT models by 1.09 and 4.18 percentage points, respectively. GFN offers an efficient and reliable solution for waste classification, highlighting the potential of deep learning in environmental protection.","manuscriptTitle":"Garbage FusionNet: A deep learning framework combining ResNet and Vision Transformer for waste classification","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-08-02 10:40:38","doi":"10.21203/rs.3.rs-4708918/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":"cf03bc67-5128-4a08-9c16-f189deb9b316","owner":[],"postedDate":"August 2nd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":35413684,"name":"Earth and environmental sciences/Environmental sciences"},{"id":35413685,"name":"Earth and environmental sciences/Environmental social sciences"}],"tags":[],"updatedAt":"2024-12-31T17:12:23+00:00","versionOfRecord":{"articleIdentity":"rs-4708918","link":"https://doi.org/10.3390/electronics14010075","journal":{"identity":"electronics","isVorOnly":true,"title":"Electronics"},"publishedOn":"2024-12-27 00:00:00","publishedOnDateReadable":"December 27th, 2024"},"versionCreatedAt":"2024-08-02 10:40:38","video":"","vorDoi":"10.3390/electronics14010075","vorDoiUrl":"https://doi.org/10.3390/electronics14010075","workflowStages":[]},"version":"v1","identity":"rs-4708918","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4708918","identity":"rs-4708918","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}