CREST-Former: A Region-Enhanced Swin Transformer for Pest Recognition Based on Contrastive Learning

CREST-Former: A Region-Enhanced Swin Transformer for Pest Recognition Based on Contrastive Learning | 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 CREST-Former: A Region-Enhanced Swin Transformer for Pest Recognition Based on Contrastive Learning JiXiang Zou, WenZhong Yang, YaBo Yin, ZhiShan Feng, ChuangXiang Li This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6644439/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 10 You are reading this latest preprint version Abstract Transformers with long-range dependency capabilities provide effective means for pest classification in agricultural engineering. However, their self-attention mechanism often causes query tokens to overly focus on local image patches, limiting the effective receptive field. To address this challenge, this paper proposes a novel Region-Enhanced Swin Transformer for Pest Recognition Based on Contrastive Learning (CREST-Former) architecture, which enhances pest identification through innovative attention mechanisms and multi-scale feature extraction. Our network integrates three innovative modules: ( 1 ) PDSwin Transformer block, utilizing multi-receptive field depth-separable convolution and self-attention mechanisms to simultaneously capture features at different scales, enhancing the model’s perception ability for minute morphological features of insects; ( 2 ) Discriminant Region Enhancement Module (DREM) that automatically identifies the most distinctive regions of pest morphology to improve classification accuracy.( 3 ) we also design a discriminative region-guided contrastive learning framework, significantly improving feature intra-class compactness and inter-class separability. Experiments show that CREST-Former achieves classification accuracies of 76.13%, 99.85%, and 79.16% on the IP102, D0, and CPB datasets, respectively. Heatmap visualization confirms that the model precisely focuses on discriminative morphological regions of pests, and it has been successfully deployed on the Jetson Nano platform for practical applications. Earth and environmental sciences/Ecology/Agri ecology Physical sciences/Mathematics and computing/Computer science Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 17 Sep, 2025 Reviews received at journal 04 Sep, 2025 Reviewers agreed at journal 02 Sep, 2025 Reviews received at journal 26 Aug, 2025 Reviewers agreed at journal 14 Aug, 2025 Reviewers invited by journal 13 Aug, 2025 Editor assigned by journal 06 Aug, 2025 Editor invited by journal 26 May, 2025 Submission checks completed at journal 23 May, 2025 First submitted to journal 12 May, 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-6644439","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":500532089,"identity":"0fd73c45-f259-425e-8824-b480e06e6029","order_by":0,"name":"JiXiang Zou","email":"","orcid":"","institution":"Xinjiang University","correspondingAuthor":false,"prefix":"","firstName":"JiXiang","middleName":"","lastName":"Zou","suffix":""},{"id":500532090,"identity":"13123e25-a353-41d5-b9be-4c6657d92033","order_by":1,"name":"WenZhong Yang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+ElEQVRIiWNgGAWjYDADAxDxgYENziZOC+MMkrUw8yDZiFvl8bOHX/NU3LE3Z+89/Nq2jS+xgb15mwRDzR3cWs7kpVnznHnGbNlzLs065wxbYgPPsTIJhmPPcGs5kGNmnNt2mM3gBpCRUwHUIpFjJsHYcBi3lvNvgFr+HeYBa7EwAGqRf0NAy40c48e5DYclwAwGsC08+LVI3nhjxvzn2GEDgzNnzBh7zrAZt/GkFVskHMOthe98jvHHGTWH7Q2O9xh/+Nl2TLaf/fDGGx9qcGtROMDAJgFlgxjHIJGZgFMDA4N8AwPzBygbxKjBo3YUjIJRMApGKgAA5GlXL250Gt8AAAAASUVORK5CYII=","orcid":"","institution":"Xinjiang University","correspondingAuthor":true,"prefix":"","firstName":"WenZhong","middleName":"","lastName":"Yang","suffix":""},{"id":500532093,"identity":"61d705fc-f2d6-4959-8bac-61a9916b54af","order_by":2,"name":"YaBo Yin","email":"","orcid":"","institution":"Xinjiang University","correspondingAuthor":false,"prefix":"","firstName":"YaBo","middleName":"","lastName":"Yin","suffix":""},{"id":500532094,"identity":"3a9bc6b8-0533-4005-b58b-d6d470d5391f","order_by":3,"name":"ZhiShan Feng","email":"","orcid":"","institution":"Xinjiang University","correspondingAuthor":false,"prefix":"","firstName":"ZhiShan","middleName":"","lastName":"Feng","suffix":""},{"id":500532096,"identity":"42c2e565-1b60-49c7-9304-e4dd9f6e73ee","order_by":4,"name":"ChuangXiang Li","email":"","orcid":"","institution":"Xinjiang University","correspondingAuthor":false,"prefix":"","firstName":"ChuangXiang","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2025-05-12 08:23:25","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6644439/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6644439/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":89594411,"identity":"582debab-de63-4196-a825-05c40ea711c4","added_by":"auto","created_at":"2025-08-21 16:30:36","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1277585,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6644439/v1_covered_31295d9c-f6c8-4c79-9845-cfb99ccfacca.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"CREST-Former: A Region-Enhanced Swin Transformer for Pest Recognition Based on Contrastive Learning","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":"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":"","lastPublishedDoi":"10.21203/rs.3.rs-6644439/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6644439/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eTransformers with long-range dependency capabilities provide effective means for pest classification in agricultural engineering. However, their self-attention mechanism often causes query tokens to overly focus on local image patches, limiting the effective receptive field. To address this challenge, this paper proposes a novel Region-Enhanced Swin Transformer for Pest Recognition Based on Contrastive Learning (CREST-Former) architecture, which enhances pest identification through innovative attention mechanisms and multi-scale feature extraction. Our network integrates three innovative modules: (\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e) PDSwin Transformer block, utilizing multi-receptive field depth-separable convolution and self-attention mechanisms to simultaneously capture features at different scales, enhancing the model\u0026rsquo;s perception ability for minute morphological features of insects; (\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e) Discriminant Region Enhancement Module (DREM) that automatically identifies the most distinctive regions of pest morphology to improve classification accuracy.(\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e) we also design a discriminative region-guided contrastive learning framework, significantly improving feature intra-class compactness and inter-class separability. Experiments show that CREST-Former achieves classification accuracies of 76.13%, 99.85%, and 79.16% on the IP102, D0, and CPB datasets, respectively. Heatmap visualization confirms that the model precisely focuses on discriminative morphological regions of pests, and it has been successfully deployed on the Jetson Nano platform for practical applications.\u003c/p\u003e","manuscriptTitle":"CREST-Former: A Region-Enhanced Swin Transformer for Pest Recognition Based on Contrastive Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-21 15:58:29","doi":"10.21203/rs.3.rs-6644439/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-09-18T03:03:49+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-04T06:50:55+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"104478307801461857703477890410699234292","date":"2025-09-02T22:57:11+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-08-27T02:41:01+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"130173798269861087465911414904697422409","date":"2025-08-14T12:25:58+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-08-13T09:18:18+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-08-06T07:50:58+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-05-26T12:12:08+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-05-23T14:40:08+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-05-12T08:15:51+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":"0844fc39-ffa2-4bbd-a755-54f5d77ae999","owner":[],"postedDate":"August 21st, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":53174120,"name":"Earth and environmental sciences/Ecology/Agri ecology"},{"id":53174121,"name":"Physical sciences/Mathematics and computing/Computer science"}],"tags":[],"updatedAt":"2026-01-23T04:24:32+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-21 15:58:29","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6644439","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6644439","identity":"rs-6644439","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}