Data-Efficient and Accurate Rapeseed Leaf Area Estimation by Self-supervised Vision Transformer for Germplasms Early Evaluation

Data-Efficient and Accurate Rapeseed Leaf Area Estimation by Self-supervised Vision Transformer for Germplasms Early Evaluation | 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 Data-Efficient and Accurate Rapeseed Leaf Area Estimation by Self-supervised Vision Transformer for Germplasms Early Evaluation Pengfei Hao, Jianpeng An, Qing Cai, Junqin Cao, Chaochao He, Zhiqi Ma, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7278813/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 05 Dec, 2025 Read the published version in Plant Methods → Version 1 posted 15 You are reading this latest preprint version Abstract Early-stage, accurate and high-throughput phenotyping‌ through leaf area estimation is ‌critical‌ for future rapeseed breeding, but faces ‌two key constraints‌: expensive data annotation and persistent challenge of leaf occlusion. To address these issues, we present a ‌data-efficient‌ deep learning framework using smartphone-captured top-down RGB images for rapeseed leaf area quantification. Our approach utilizes a two-stage strategy where a Vision Transformer (ViT) backbone is first pre-trained on a large, aggregated corpus of diverse, non-rapeseed public plant datasets using the DINOv2 self-supervised learning method. This pre-trained model is then fine-tuned on a custom rapeseed dataset using a novel Canopy-Mix data augmentation technique to handle fragmented views analogous to occlusion, and a hybrid loss function combining Smooth L1 and Log-Cosh for robust convergence. Through rigorous 5-fold cross-validation, our proposed model achieved state-of-the-art predictive performance (Coefficient of Determination, R$^2$=0.805). What’s more, the predicted leaf area demonstrated a remarkably strong correlation with both fresh weight (r=0.900) and dry weight (r=0.885). The model significantly outperformed a range of baselines, including models trained from scratch, those pre-trained on ImageNet, and a heuristic method based on manually annotated bounding boxes. Ablation studies confirmed the essential contribution of each component, while qualitative analysis of attention maps demonstrated the model's ability to precisely localize the leaf canopy and ignore background distractors. This study demonstrates that domain-specific self-supervised pre-training offers a powerful solution to overcome data limitations in agricultural vision, providing a robust and scalable tool for non-destructive phenotyping that can potentially accelerate the rapeseed breeding cycle. Deep Learning Leaf Area Estimation Self-Supervised Learning Plant Phenotyping Rapeseed Breeding Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 05 Dec, 2025 Read the published version in Plant Methods → Version 1 posted Editorial decision: Revision requested 02 Sep, 2025 Reviews received at journal 02 Sep, 2025 Reviews received at journal 24 Aug, 2025 Reviews received at journal 23 Aug, 2025 Reviews received at journal 18 Aug, 2025 Reviewers agreed at journal 14 Aug, 2025 Reviewers agreed at journal 12 Aug, 2025 Reviewers agreed at journal 12 Aug, 2025 Reviewers agreed at journal 12 Aug, 2025 Reviewers agreed at journal 12 Aug, 2025 Reviewers agreed at journal 12 Aug, 2025 Reviewers invited by journal 11 Aug, 2025 Editor assigned by journal 06 Aug, 2025 Submission checks completed at journal 06 Aug, 2025 First submitted to journal 02 Aug, 2025 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-7278813","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":501749664,"identity":"b464d916-b04f-4b7d-a13d-e9e84c6a57a5","order_by":0,"name":"Pengfei Hao","email":"","orcid":"","institution":"Zhejiang Academy of Agricultural Sciences","correspondingAuthor":false,"prefix":"","firstName":"Pengfei","middleName":"","lastName":"Hao","suffix":""},{"id":501749666,"identity":"9146039f-0d8a-4177-8f51-654cf78cf757","order_by":1,"name":"Jianpeng An","email":"","orcid":"","institution":"Tianjin University","correspondingAuthor":false,"prefix":"","firstName":"Jianpeng","middleName":"","lastName":"An","suffix":""},{"id":501749667,"identity":"3aadb180-c12a-4ce3-8404-e4276db4ac2d","order_by":2,"name":"Qing Cai","email":"","orcid":"","institution":"Tiangong University","correspondingAuthor":false,"prefix":"","firstName":"Qing","middleName":"","lastName":"Cai","suffix":""},{"id":501749668,"identity":"4c52b8af-1e54-448d-ad55-5b3ce38b301a","order_by":3,"name":"Junqin Cao","email":"","orcid":"","institution":"Zhejiang Academy of Agricultural Sciences","correspondingAuthor":false,"prefix":"","firstName":"Junqin","middleName":"","lastName":"Cao","suffix":""},{"id":501749669,"identity":"aec3c43f-507a-418c-8f70-f8bfb1c6234a","order_by":4,"name":"Chaochao He","email":"","orcid":"","institution":"Zhejiang Academy of Agricultural Sciences","correspondingAuthor":false,"prefix":"","firstName":"Chaochao","middleName":"","lastName":"He","suffix":""},{"id":501749672,"identity":"c295f463-524a-4e4f-ba56-960c2e0111ef","order_by":5,"name":"Zhiqi Ma","email":"","orcid":"","institution":"Zhejiang Academy of Agricultural Sciences","correspondingAuthor":false,"prefix":"","firstName":"Zhiqi","middleName":"","lastName":"Ma","suffix":""},{"id":501749680,"identity":"62471c71-f603-445b-88d1-e7ac275d57a5","order_by":6,"name":"Shuijin Hua","email":"","orcid":"","institution":"Zhejiang Academy of Agricultural Sciences","correspondingAuthor":false,"prefix":"","firstName":"Shuijin","middleName":"","lastName":"Hua","suffix":""},{"id":501749681,"identity":"6feb96ef-a636-4d81-9f35-cec7b0b10751","order_by":7,"name":"Baogang Lin","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAqklEQVRIiWNgGAWjYBACAwbmhgMMFRJy/CRoYQRqOWNhLNlAihYGxraKxA1EazHnX9h4uHCeBOMGBuaHj24Qo8VyxsOGwzO3STCbM7AZG+cQ5bAbBxsO826TYLNs4GGTJkHLHAkegwNEaznfCNTSICFBvBbLGYwNh3mOSRhINhPrF3P+w4c/89TU1fezNz98TJQWBokEKIOZKOUgwH+AaKWjYBSMglEwUgEAvNox5jSAtXkAAAAASUVORK5CYII=","orcid":"","institution":"Zhejiang Academy of Agricultural Sciences","correspondingAuthor":true,"prefix":"","firstName":"Baogang","middleName":"","lastName":"Lin","suffix":""}],"badges":[],"createdAt":"2025-08-02 14:23:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7278813/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7278813/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s13007-025-01478-2","type":"published","date":"2025-12-05T15:56:55+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":97724660,"identity":"aa1a2391-f9f9-4bcb-9c4b-c9c381443f52","added_by":"auto","created_at":"2025-12-08 16:13:13","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":6687898,"visible":true,"origin":"","legend":"","description":"","filename":"rapeseed2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7278813/v1_covered_7e186790-42ae-4165-9e90-3ef56372d0d0.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Data-Efficient and Accurate Rapeseed Leaf Area Estimation by Self-supervised Vision Transformer for Germplasms Early Evaluation","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":"Deep Learning, Leaf Area Estimation, Self-Supervised Learning, Plant Phenotyping, Rapeseed, Breeding","lastPublishedDoi":"10.21203/rs.3.rs-7278813/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7278813/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Early-stage, accurate and high-throughput phenotyping‌ through leaf area estimation is ‌critical‌ for future rapeseed breeding, but faces ‌two key constraints‌: expensive data annotation and persistent challenge of leaf occlusion. To address these issues, we present a ‌data-efficient‌ deep learning framework using smartphone-captured top-down RGB images for rapeseed leaf area quantification. Our approach utilizes a two-stage strategy where a Vision Transformer (ViT) backbone is first pre-trained on a large, aggregated corpus of diverse, non-rapeseed public plant datasets using the DINOv2 self-supervised learning method. This pre-trained model is then fine-tuned on a custom rapeseed dataset using a novel Canopy-Mix data augmentation technique to handle fragmented views analogous to occlusion, and a hybrid loss function combining Smooth L1 and Log-Cosh for robust convergence. Through rigorous 5-fold cross-validation, our proposed model achieved state-of-the-art predictive performance (Coefficient of Determination, R$^2$=0.805). What’s more, the predicted leaf area demonstrated a remarkably strong correlation with both fresh weight (r=0.900) and dry weight (r=0.885). The model significantly outperformed a range of baselines, including models trained from scratch, those pre-trained on ImageNet, and a heuristic method based on manually annotated bounding boxes. Ablation studies confirmed the essential contribution of each component, while qualitative analysis of attention maps demonstrated the model's ability to precisely localize the leaf canopy and ignore background distractors. This study demonstrates that domain-specific self-supervised pre-training offers a powerful solution to overcome data limitations in agricultural vision, providing a robust and scalable tool for non-destructive phenotyping that can potentially accelerate the rapeseed breeding cycle.","manuscriptTitle":"Data-Efficient and Accurate Rapeseed Leaf Area Estimation by Self-supervised Vision Transformer for Germplasms Early Evaluation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-20 18:14:27","doi":"10.21203/rs.3.rs-7278813/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-09-02T13:44:51+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-02T05:53:21+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-08-24T14:05:28+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-08-23T19:37:54+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-08-18T07:04:18+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"310639489422644233809267153308942860635","date":"2025-08-14T06:51:39+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"103636469823921587808335599003873561255","date":"2025-08-12T18:58:14+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"190725760326913340622617851386961505649","date":"2025-08-12T11:48:32+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"180353687954438815843750015919825474849","date":"2025-08-12T09:15:36+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"66789586377271562481087394938079455521","date":"2025-08-12T06:09:55+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"133525913889610369866749298099498428179","date":"2025-08-12T05:55:14+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-08-12T03:28:04+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-08-06T14:21:38+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-08-06T14:20:20+00:00","index":"","fulltext":""},{"type":"submitted","content":"Plant Methods","date":"2025-08-02T14:10:05+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":"ed2f41d6-19e3-4ab5-97b0-82b493227a72","owner":[],"postedDate":"August 20th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-12-08T16:10:37+00:00","versionOfRecord":{"articleIdentity":"rs-7278813","link":"https://doi.org/10.1186/s13007-025-01478-2","journal":{"identity":"plant-methods","isVorOnly":false,"title":"Plant Methods"},"publishedOn":"2025-12-05 15:56:55","publishedOnDateReadable":"December 5th, 2025"},"versionCreatedAt":"2025-08-20 18:14:27","video":"","vorDoi":"10.1186/s13007-025-01478-2","vorDoiUrl":"https://doi.org/10.1186/s13007-025-01478-2","workflowStages":[]},"version":"v1","identity":"rs-7278813","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7278813","identity":"rs-7278813","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}