A lightweight convolutional and vision transformer hybrid network for parameter efficient plant disease classification

A lightweight convolutional and vision transformer hybrid network for parameter efficient plant disease 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 A lightweight convolutional and vision transformer hybrid network for parameter efficient plant disease classification Thanh-Hai Tong-Le, Minh-Hai Le, Thanh-Nghi Doan This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9235961/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 14 You are reading this latest preprint version Abstract Accurate plant disease classification for edge deployment requires models that are both precise and efficient. Convolutional neural networks (CNNs) learn local lesion patterns effectively. Pure Transformers capture global dependencies more explicitly, but they typically incur a higher computational cost. We propose CViTLw, a lightweight CNN-Transformer hybrid comprising a MobileNetV2 branch, a compact Vision Transformer branch, and an attention-enhanced cross-fusion module. We further evaluate two lightweight attention mechanisms, SE and CBAM, within the same framework. Experiments on the PlantVillage and Maize Leaf Disease datasets are conducted under both controlled and field-acquired conditions. On the Maize Leaf Disease dataset, CViTLw-SE attains 94.85% accuracy with only 0.33M parameters. On PlantVillage, both CViTLw-SE and CViTLw-CB achieve 99.74% accuracy (as well as precision, recall, and F1-score) and an AUC of 100%. The most compact variants operate in less than 2 ms per image and exceed 500 FPS. Overall, CViTLw achieves a strong balance of accuracy, efficiency, and practical deployability. The source code is publicly available at \href{https://drive.google.com/file/d/1nHDZNomhAC7GNLEdAeMyH7qJq3yqh45W/view?usp=drive_link}{this link}. plant disease classification lightweight CNN–Transformer attention mechanisms edge AI explainable AI Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 17 Apr, 2026 Reviews received at journal 15 Apr, 2026 Reviews received at journal 13 Apr, 2026 Reviews received at journal 13 Apr, 2026 Reviewers agreed at journal 12 Apr, 2026 Reviews received at journal 11 Apr, 2026 Reviewers agreed at journal 10 Apr, 2026 Reviewers agreed at journal 10 Apr, 2026 Reviewers agreed at journal 10 Apr, 2026 Reviewers agreed at journal 10 Apr, 2026 Reviewers invited by journal 10 Apr, 2026 Editor assigned by journal 08 Apr, 2026 Submission checks completed at journal 07 Apr, 2026 First submitted to journal 07 Apr, 2026 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-9235961","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":624666236,"identity":"0f33e949-24f9-4925-a7fb-e649996ccb11","order_by":0,"name":"Thanh-Hai Tong-Le","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABDElEQVRIiWNgGAWjYLCCBwwMCQwMPGwMDAY2EBEePKrBcgkMBjAtaRKkamE4TFiLPXvv4RcJFX/y+Gf3Hnvwo+B8nXxEAuODt20Midtx2cJzLs0i4YxBscSdc+mGPQa3JQxvJDAbzgVq2dmAQ4tEjplBYptBYsONHDMJHpCWGQls0rxtDMYGB/Bp+WeQOB+oRfKPwTmQFvbfBLQYP0hsMEjcANQizWNwQEJeIoGNGahFDqeWM2fMGBKOGSduBGmRMUiW3MDzsFlyzjkJnFrY23uMP3yokUucB3LYmz92/PLtyQc/vCmz4cGlBQjYJFC4BgcYG4CUBFa1UMD8AYUr34BP8SgYBaNgFIxEAAABcFjCr+2IigAAAABJRU5ErkJggg==","orcid":"","institution":"College of Engineering and Technology, Tra Vinh University","correspondingAuthor":true,"prefix":"","firstName":"Thanh-Hai","middleName":"","lastName":"Tong-Le","suffix":""},{"id":624666237,"identity":"9314304c-af70-4ac1-8d95-ea700a1b7abd","order_by":1,"name":"Minh-Hai Le","email":"","orcid":"","institution":"College of Engineering and Technology, Tra Vinh University","correspondingAuthor":false,"prefix":"","firstName":"Minh-Hai","middleName":"","lastName":"Le","suffix":""},{"id":624666238,"identity":"23c2b668-5eb0-4a22-b333-e88946f7c394","order_by":2,"name":"Thanh-Nghi Doan","email":"","orcid":"","institution":"An Giang University, Vietnam National University","correspondingAuthor":false,"prefix":"","firstName":"Thanh-Nghi","middleName":"","lastName":"Doan","suffix":""}],"badges":[],"createdAt":"2026-03-26 15:25:54","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9235961/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9235961/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107483671,"identity":"6b72645f-7c8d-4227-967e-286f71254e7e","added_by":"auto","created_at":"2026-04-22 02:28:43","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":15136078,"visible":true,"origin":"","legend":"","description":"","filename":"CViTLwv7EN.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9235961/v1_covered_382a7898-a687-4064-acaf-e449d7f4bae4.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A lightweight convolutional and vision transformer hybrid network for parameter efficient plant disease classification","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"discover-artificial-intelligence","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"diai","sideBox":"Learn more about [Discover Artificial Intelligence](https://www.springer.com/44163)","snPcode":"","submissionUrl":"","title":"Discover Artificial Intelligence","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Discover Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"plant disease classification, lightweight CNN–Transformer, attention mechanisms, edge AI, explainable AI","lastPublishedDoi":"10.21203/rs.3.rs-9235961/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9235961/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAccurate plant disease classification for edge deployment requires models that are both precise and efficient. Convolutional neural networks (CNNs) learn local lesion patterns effectively. Pure Transformers capture global dependencies more explicitly, but they typically incur a higher computational cost. We propose CViTLw, a lightweight CNN-Transformer hybrid comprising a MobileNetV2 branch, a compact Vision Transformer branch, and an attention-enhanced cross-fusion module. We further evaluate two lightweight attention mechanisms, SE and CBAM, within the same framework. Experiments on the PlantVillage and Maize Leaf Disease datasets are conducted under both controlled and field-acquired conditions. On the Maize Leaf Disease dataset, CViTLw-SE attains 94.85% accuracy with only 0.33M parameters. On PlantVillage, both CViTLw-SE and CViTLw-CB achieve 99.74% accuracy (as well as precision, recall, and F1-score) and an AUC of 100%. The most compact variants operate in less than 2 ms per image and exceed 500 FPS. Overall, CViTLw achieves a strong balance of accuracy, efficiency, and practical deployability. The source code is publicly available at \\href{https://drive.google.com/file/d/1nHDZNomhAC7GNLEdAeMyH7qJq3yqh45W/view?usp=drive_link}{this link}.\u003c/p\u003e","manuscriptTitle":"A lightweight convolutional and vision transformer hybrid network for parameter efficient plant disease classification","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-17 18:30:16","doi":"10.21203/rs.3.rs-9235961/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-04-17T04:34:11+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-16T02:25:56+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-13T16:37:26+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-13T07:49:08+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"109836332158652213130611520273538750679","date":"2026-04-12T22:16:15+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-11T14:43:34+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"324282953271666330320478638633033408390","date":"2026-04-11T02:16:06+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"147737999501095412547944243914772546471","date":"2026-04-10T13:58:49+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"14461457135168045246477989274450791783","date":"2026-04-10T12:04:48+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"62098894549797738476621933981272029788","date":"2026-04-10T10:38:10+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-10T10:30:29+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-08T04:21:08+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-07T11:57:05+00:00","index":"","fulltext":""},{"type":"submitted","content":"Discover Artificial Intelligence","date":"2026-04-07T09:32:45+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"discover-artificial-intelligence","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"diai","sideBox":"Learn more about [Discover Artificial Intelligence](https://www.springer.com/44163)","snPcode":"","submissionUrl":"","title":"Discover Artificial Intelligence","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Discover Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"9abf604b-f593-4074-9931-2bb0d44dcef2","owner":[],"postedDate":"April 17th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-07T13:39:47+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-17 18:30:16","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9235961","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9235961","identity":"rs-9235961","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}