A Compact Deep Learning Approach Integrating Depthwise Convolutions and Spatial Attention for Plant Disease Classification

A Compact Deep Learning Approach Integrating Depthwise Convolutions and Spatial Attention for 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 Compact Deep Learning Approach Integrating Depthwise Convolutions and Spatial Attention for Plant Disease Classification Amreen Batool, Joon-Min Gil, Yung-Cheol Byun This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5392998/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 02 Apr, 2025 Read the published version in Plant Methods → Version 1 posted 4 You are reading this latest preprint version Abstract Agriculture is a major sector that provides food to the growing worldpopulation, so improving crop yields from the disease is essential. Bac-terial, fungi and viral plant diseases significantly challenge high cropproductivity. Traditional methods of plant disease detection are time-consuming and require expert knowledge. Therefore, to ensure optimalcrop health and yield, advanced, efficient, and accurate methods areneeded to detect and classify plant diseases early and accurately. Thisreview article explores the recent advancements in vision-based machinelearning (ML) and deep learning (DL) techniques for detecting plantleaf diseases. Specifically, the objective is to provide a detailed overviewof the current state-of-the-art methodologies, assess their effectiveness,and identify the role of critical datasets in facilitating these advance-ments. Additionally, the article highlights the potential of integratingemerging technologies, such as vision based models, to enhance diseasedetection systems’ capabilities. The review systematically examines var-ious ML and DL techniques for plant leaf disease detection, focusingon their application and performance. Techniques such as Convolu-tional Neural Networks (CNNs), which have shown high accuracy in disease identification, are discussed in depth. The importance of open-source databases, particularly PlantVillage, in training and validatingthese models is emphasized. The methodology also discusses integrat-ing advanced technologies and developing hybrid models that combinevision-based and language-based approaches to improve detection accu-racy and robustness. The analysis highlights the significant progressin applying ML and DL to plant leaf disease detection, showcasingseveral successful implementations and their outcomes. The reviewidentifies emerging trends that promise to enhance disease detectionsystems. It also critically assesses the strengths and limitations ofcurrent techniques, offering insights into potential improvements andfuture research directions. This comprehensive analysis highlights thecritical role of ML and DL in advancing plant disease detection, aim-ing to provide sustainable and scalable solutions for the agriculturalsector. The findings have significant implications for improving cropyields and ensuring food security for the growing global population. Agriculture Plant leaf disease Deptwise Spareabale convolutional Spatial attention MobileNet Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 02 Apr, 2025 Read the published version in Plant Methods → Version 1 posted Editorial decision: Revision requested 13 Nov, 2024 Editor assigned by journal 13 Nov, 2024 Submission checks completed at journal 12 Nov, 2024 First submitted to journal 05 Nov, 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-5392998","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":377849273,"identity":"2de46e28-ad99-4709-b18b-0274e6d1db48","order_by":0,"name":"Amreen Batool","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+ElEQVRIiWNgGAWjYPACGzBpwMADEzhAUEsaWDFJWg4jFBPUwj/t7MMHH3ect7eXSGAo+CBzOM/gAPPDDwxn7uHUInE73dhw5pnbiT1ALYYzeA4XGxxgM5ZguFGM25rbaWzSvG23E3iAWox5eA4nbjjAYMbA8CEBpw7522nsv/+2nbMHa/kD1sL+Da8WA6AtzIxtBxhBDjNmAGvhAdpyA7cWw9tpzJK9bcmJPWceNhj28KQnzjzMUyyRcAa3FrnbaYwffrbZ2bO3Jx8z+Nljndh3vH3jhw/HcGtBAoxtBow9QJoZiInSAFL7gOEHkUpHwSgYBaNgRAEA7PRUQcx5BiYAAAAASUVORK5CYII=","orcid":"","institution":"Jeju National University","correspondingAuthor":true,"prefix":"","firstName":"Amreen","middleName":"","lastName":"Batool","suffix":""},{"id":377849274,"identity":"efdfd8b4-7966-4b74-b262-0369def189b4","order_by":1,"name":"Joon-Min Gil","email":"","orcid":"","institution":"Jeju National University","correspondingAuthor":false,"prefix":"","firstName":"Joon-Min","middleName":"","lastName":"Gil","suffix":""},{"id":377849275,"identity":"6671f293-40b8-423c-aa22-36beb4594a77","order_by":2,"name":"Yung-Cheol Byun","email":"","orcid":"","institution":"Jeju National University","correspondingAuthor":false,"prefix":"","firstName":"Yung-Cheol","middleName":"","lastName":"Byun","suffix":""}],"badges":[],"createdAt":"2024-11-05 07:23:06","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5392998/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5392998/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s13007-025-01325-4","type":"published","date":"2025-04-02T15:57:46+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":80082081,"identity":"63fb1ce5-00fe-4c13-a938-5fb78f964ed5","added_by":"auto","created_at":"2025-04-07 16:06:50","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":5498731,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5392998/v1_covered_c5f9b7bd-bd9a-4346-9848-eb935efdfcc1.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Compact Deep Learning Approach Integrating Depthwise Convolutions and Spatial Attention for Plant Disease 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":"plant-methods","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"plme","sideBox":"Learn more about [Plant Methods](http://plantmethods.biomedcentral.com/)","snPcode":"13007","submissionUrl":"https://submission.nature.com/new-submission/13007/3","title":"Plant Methods","twitterHandle":"@PlantMethods","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Agriculture, Plant leaf disease, Deptwise Spareabale convolutional, Spatial attention, MobileNet","lastPublishedDoi":"10.21203/rs.3.rs-5392998/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5392998/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Agriculture is a major sector that provides food to the growing worldpopulation, so improving crop yields from the disease is essential. Bac-terial, fungi and viral plant diseases significantly challenge high cropproductivity. Traditional methods of plant disease detection are time-consuming and require expert knowledge. Therefore, to ensure optimalcrop health and yield, advanced, efficient, and accurate methods areneeded to detect and classify plant diseases early and accurately. Thisreview article explores the recent advancements in vision-based machinelearning (ML) and deep learning (DL) techniques for detecting plantleaf diseases. Specifically, the objective is to provide a detailed overviewof the current state-of-the-art methodologies, assess their effectiveness,and identify the role of critical datasets in facilitating these advance-ments. Additionally, the article highlights the potential of integratingemerging technologies, such as vision based models, to enhance diseasedetection systems’ capabilities. The review systematically examines var-ious ML and DL techniques for plant leaf disease detection, focusingon their application and performance. Techniques such as Convolu-tional Neural Networks (CNNs), which have shown high accuracy in disease identification, are discussed in depth. The importance of open-source databases, particularly PlantVillage, in training and validatingthese models is emphasized. The methodology also discusses integrat-ing advanced technologies and developing hybrid models that combinevision-based and language-based approaches to improve detection accu-racy and robustness. The analysis highlights the significant progressin applying ML and DL to plant leaf disease detection, showcasingseveral successful implementations and their outcomes. The reviewidentifies emerging trends that promise to enhance disease detectionsystems. It also critically assesses the strengths and limitations ofcurrent techniques, offering insights into potential improvements andfuture research directions. This comprehensive analysis highlights thecritical role of ML and DL in advancing plant disease detection, aim-ing to provide sustainable and scalable solutions for the agriculturalsector. The findings have significant implications for improving cropyields and ensuring food security for the growing global population.","manuscriptTitle":"A Compact Deep Learning Approach Integrating Depthwise Convolutions and Spatial Attention for Plant Disease Classification","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-12-05 05:33:57","doi":"10.21203/rs.3.rs-5392998/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-11-13T21:34:46+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-11-13T21:33:39+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-11-13T04:07:01+00:00","index":"","fulltext":""},{"type":"submitted","content":"Plant Methods","date":"2024-11-05T07:07:20+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"plant-methods","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"plme","sideBox":"Learn more about [Plant Methods](http://plantmethods.biomedcentral.com/)","snPcode":"13007","submissionUrl":"https://submission.nature.com/new-submission/13007/3","title":"Plant Methods","twitterHandle":"@PlantMethods","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"9e01eedb-1555-47ce-8dfd-5cc6421ffd22","owner":[],"postedDate":"December 5th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-04-07T16:02:17+00:00","versionOfRecord":{"articleIdentity":"rs-5392998","link":"https://doi.org/10.1186/s13007-025-01325-4","journal":{"identity":"plant-methods","isVorOnly":false,"title":"Plant Methods"},"publishedOn":"2025-04-02 15:57:46","publishedOnDateReadable":"April 2nd, 2025"},"versionCreatedAt":"2024-12-05 05:33:57","video":"","vorDoi":"10.1186/s13007-025-01325-4","vorDoiUrl":"https://doi.org/10.1186/s13007-025-01325-4","workflowStages":[]},"version":"v1","identity":"rs-5392998","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5392998","identity":"rs-5392998","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}