VMUnet-MSADI： Visual Mamba UNet Fusion Multi-Scale Attention and Detail Infusion for Unsound Corn Kernels Segmentation

VMUnet-MSADI： Visual Mamba UNet Fusion Multi-Scale Attention and Detail Infusion for Unsound Corn Kernels Segmentation | 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 VMUnet-MSADI： Visual Mamba UNet Fusion Multi-Scale Attention and Detail Infusion for Unsound Corn Kernels Segmentation Kuibin Zhao, Qinghui Zhang, Chenxia Wan, Quan Pan, Yao Qin This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5170853/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 29 Mar, 2025 Read the published version in Scientific Reports → Version 1 posted 10 You are reading this latest preprint version Abstract Corn seed breeding is a global issue, and has attracted great attention in recent years. Deploying autonomous robots for corn kernel recognition and classification has great potential in terms of constructing environment friendly agriculture, and saving manpower. Existing segmentation methods that utilize U-shaped architectures typically operate by processing images in discrete pixel-based segments. This approach often overlooks the finer pixel-level structural details within these segments, leading to models that struggle to preserve the continuity of target edges effectively. In this paper, we propose a new framework for corn seed image segmentation, called VMUnet-MSADI, which aims to integrate MSADI module into the encoder and decoder of the VMUnet architecture. Our VMUnet-MSADI model benefits from self-attention computation in VMUnet and multiscale coding to efficiently model non-local dependencies and multiscale contexts to improve the segmentation quality of different images. Unlike previous Unet-based improvement schemes, the proposed VMUnet-MSADI adopts a multiscale convolutional attention module coding mechanism at the depth level and an efficient multiscale deep convolutional decoder at the spatial level to extract coarse-grained features and fine-grained features at different semantic scales and effectively avoid the loss of information at the target boundary to improve the quality and accuracy of target segmentation. In addition, we introduce a Visual State Space (VSS) block to capture a wide range of contextual information and a Detail Infusion Block (DIB) to enhance the fusion of low-level and high-level features, which further fills in the remote contextual information during the up-sampling process. Comprehensive experiments were conducted on open-source datasets and the results demonstrate that the VMUnet-MSADI model excels in the task of corn kernel segmentation. The model achieved a segmentation accuracy of 95.96%, surpassing the leading method by 0.9%. Compared to other segmentation models, our method exhibits superior performance in both accuracy and loss metrics. Extensive comparative experiments conducted on various benchmark datasets further substantiate that our approach outperforms the state-of-the-art models. Code, pre-trained models and data processing protocols are available at https://github.com/corbining/VMUnet-MSADI Biological sciences/Plant sciences/Plant breeding Physical sciences/Engineering/Biomedical engineering Biological sciences/Biological techniques/Software Biological sciences/Biological techniques/Imaging/Diffusion tensor imaging DeepLearning VMUnet Multi-Scale Attention Detail Infusion Unsound Corn Kernels Image Segmentation Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 29 Mar, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 20 Oct, 2024 Reviews received at journal 19 Oct, 2024 Reviews received at journal 18 Oct, 2024 Reviewers agreed at journal 18 Oct, 2024 Reviewers agreed at journal 15 Oct, 2024 Reviewers invited by journal 15 Oct, 2024 Editor assigned by journal 15 Oct, 2024 Editor invited by journal 15 Oct, 2024 Submission checks completed at journal 14 Oct, 2024 First submitted to journal 28 Sep, 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-5170853","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":368280285,"identity":"5cad25ca-2b13-4591-af0e-c3b3d5350a4a","order_by":0,"name":"Kuibin Zhao","email":"","orcid":"","institution":"Henan University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Kuibin","middleName":"","lastName":"Zhao","suffix":""},{"id":368280286,"identity":"9b437ba4-f800-45b1-a669-5ff8a843e8a4","order_by":1,"name":"Qinghui Zhang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAs0lEQVRIie3PMQrCQBBA0V0WUo1suwEhVxiwECHoVRYEqwg5wkKKNB4gXsR6lvTxALmCyKa3UBHBRhg7i/nVFPMYRilJ+stAxYQlWBv4RPeu3s3zjvjEEKS+xOCZoGj3RA7PgIp0mioG0YerpxpHWJpg8uOJQYyr8HFlhFWgzMw4JHsSwAGQPJPAi9APxMEFe4dbyLvY8H4p2moxpdt6Y20T08QhSvn3oANr/5NIkiRJX7oDd3s1Xz+lwM0AAAAASUVORK5CYII=","orcid":"","institution":"Henan University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Qinghui","middleName":"","lastName":"Zhang","suffix":""},{"id":368280287,"identity":"043d36c8-084c-4bb1-bdcf-8a392b81488c","order_by":2,"name":"Chenxia Wan","email":"","orcid":"","institution":"Henan University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Chenxia","middleName":"","lastName":"Wan","suffix":""},{"id":368280288,"identity":"7b5e43c2-69c2-4a92-940f-1ac044914e8f","order_by":3,"name":"Quan Pan","email":"","orcid":"","institution":"Henan University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Quan","middleName":"","lastName":"Pan","suffix":""},{"id":368280289,"identity":"7bb70926-fd52-4e7e-b5ab-6e4fd80c46d5","order_by":4,"name":"Yao Qin","email":"","orcid":"","institution":"Henan University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Yao","middleName":"","lastName":"Qin","suffix":""}],"badges":[],"createdAt":"2024-09-28 14:08:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5170853/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5170853/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-024-80977-z","type":"published","date":"2025-03-29T15:57:29+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":79604986,"identity":"64b1c1dd-ce58-4c29-a61d-15f1fc10a6f6","added_by":"auto","created_at":"2025-03-31 16:09:57","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1164703,"visible":true,"origin":"","legend":"","description":"","filename":"VMUnetMSADI2024.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5170853/v1_covered_71d727cf-973f-461e-89b1-96af08ebbf3d.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"VMUnet-MSADI： Visual Mamba UNet Fusion Multi-Scale Attention and Detail Infusion for Unsound Corn Kernels Segmentation","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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"DeepLearning, VMUnet, Multi-Scale Attention, Detail Infusion, Unsound Corn Kernels, Image Segmentation","lastPublishedDoi":"10.21203/rs.3.rs-5170853/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5170853/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eCorn seed breeding is a global issue, and has attracted great attention in recent years. Deploying autonomous robots for corn kernel recognition and classification has great potential in terms of constructing environment friendly agriculture, and saving manpower. Existing segmentation methods that utilize U-shaped architectures typically operate by processing images in discrete pixel-based segments. This approach often overlooks the finer pixel-level structural details within these segments, leading to models that struggle to preserve the continuity of target edges effectively. In this paper, we propose a new framework for corn seed image segmentation, called VMUnet-MSADI, which aims to integrate MSADI module into the encoder and decoder of the VMUnet architecture. Our VMUnet-MSADI model benefits from self-attention computation in VMUnet and multiscale coding to efficiently model non-local dependencies and multiscale contexts to improve the segmentation quality of different images. Unlike previous Unet-based improvement schemes, the proposed VMUnet-MSADI adopts a multiscale convolutional attention module coding mechanism at the depth level and an efficient multiscale deep convolutional decoder at the spatial level to extract coarse-grained features and fine-grained features at different semantic scales and effectively avoid the loss of information at the target boundary to improve the quality and accuracy of target segmentation. In addition, we introduce a Visual State Space (VSS) block to capture a wide range of contextual information and a Detail Infusion Block (DIB) to enhance the fusion of low-level and high-level features, which further fills in the remote contextual information during the up-sampling process. Comprehensive experiments were conducted on open-source datasets and the results demonstrate that the VMUnet-MSADI model excels in the task of corn kernel segmentation. The model achieved a segmentation accuracy of 95.96%, surpassing the leading method by 0.9%. Compared to other segmentation models, our method exhibits superior performance in both accuracy and loss metrics. Extensive comparative experiments conducted on various benchmark datasets further substantiate that our approach outperforms the state-of-the-art models. Code, pre-trained models and data processing protocols are available at \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://github.com/corbining/VMUnet-MSADI\u003c/span\u003e\u003cspan address=\"https://github.com/corbining/VMUnet-MSADI\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/p\u003e","manuscriptTitle":"VMUnet-MSADI： Visual Mamba UNet Fusion Multi-Scale Attention and Detail Infusion for Unsound Corn Kernels Segmentation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-11-04 11:09:45","doi":"10.21203/rs.3.rs-5170853/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-10-21T03:16:46+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-10-19T06:45:14+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-10-19T02:27:27+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"206905377015387174704030112016239990569","date":"2024-10-19T01:15:43+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"46204461716257915979425293122918081825","date":"2024-10-15T13:50:23+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-10-15T11:33:04+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-10-15T11:28:29+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2024-10-15T11:25:56+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-10-14T09:46:36+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2024-09-28T13:57:09+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"7d7e3a76-bee9-4de0-a8d5-a34c98a5355a","owner":[],"postedDate":"November 4th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":39184486,"name":"Biological sciences/Plant sciences/Plant breeding"},{"id":39184487,"name":"Physical sciences/Engineering/Biomedical engineering"},{"id":39184488,"name":"Biological sciences/Biological techniques/Software"},{"id":39184489,"name":"Biological sciences/Biological techniques/Imaging/Diffusion tensor imaging"}],"tags":[],"updatedAt":"2025-03-31T16:05:01+00:00","versionOfRecord":{"articleIdentity":"rs-5170853","link":"https://doi.org/10.1038/s41598-024-80977-z","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-03-29 15:57:29","publishedOnDateReadable":"March 29th, 2025"},"versionCreatedAt":"2024-11-04 11:09:45","video":"","vorDoi":"10.1038/s41598-024-80977-z","vorDoiUrl":"https://doi.org/10.1038/s41598-024-80977-z","workflowStages":[]},"version":"v1","identity":"rs-5170853","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5170853","identity":"rs-5170853","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}