Multi-view Learning for Camouflaged Object Detection with PVTv2

Multi-view Learning for Camouflaged Object Detection with PVTv2 | 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 Multi-view Learning for Camouflaged Object Detection with PVTv2 Pu Yan, Kang Ruan, Lili Wang, Yang Zhao, Xu Wang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4520181/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Recently, with the continuous development in the field of camouflage object detection(COD), effectively separating objects highly similar to the background has become a focal point of research. Due to the high similarity between camouflage objects and backgrounds, traditional single visual branch often perform poorly in such scenarios. To address this issue, We propose a multi-view learning detection network based on the Pyramid Vision Transformer, named Multi-view Learning for Camouflaged Object Detection with PVTv2(MVLNet). By utilizing the information from RGB and noise views, our method can provide a more comprehensive description of the relationship between objects and backgrounds to improve the accuracy and robustness for COD. Inspired by human visual attention during observation, we design a Global Context Aggregation Module by using a U-shaped structure and progressively increasing dilation rates to simulate the human behavior of zooming in and out. Extensive experiments demonstrate that the proposed MVLNet outperforms 22 other representative models on three public datasets. Camouflaged object detection Multi-view learning Global context aggregation module Pyramid vision transformer Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted 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-4520181","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":310012404,"identity":"d1a0369b-9172-4f5d-8ae6-2d49ca2de456","order_by":0,"name":"Pu Yan","email":"","orcid":"","institution":"Anhui Jianzhu University","correspondingAuthor":false,"prefix":"","firstName":"Pu","middleName":"","lastName":"Yan","suffix":""},{"id":310012407,"identity":"65ce4f6d-57bd-422e-84fa-a137a6625a39","order_by":1,"name":"Kang Ruan","email":"","orcid":"","institution":"Anhui Jianzhu University","correspondingAuthor":false,"prefix":"","firstName":"Kang","middleName":"","lastName":"Ruan","suffix":""},{"id":310012408,"identity":"bc93dad9-d741-4d6c-9efc-de6231f6bf6d","order_by":2,"name":"Lili Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA4ElEQVRIie3RPQrCMBTA8YRCuxRc4yBeIVKogh+9SopQlyKODg6ZuvYqWd2eFNqltWvBpS7i4NATiKkHiHETzH95CbzfkiBkMv1q7W6BKIL+aGkSRqPvSSYJ0iS0qLI7o/V4iosbQft5yJ0K1KTcRjNGL5Mjh4igchNyd8uUxIfYp5JgAZATnGQhJy5Vk/rRk3Mg4JQQ/NQhTey1jEIoILMJ5hokaB6+fLH1WkBuzVi+8RI3VpNhGntdt18tRVNcm+4wH6VOqSYym7wHAflB/fXTvszq3mPANXZNJpPpL3sBlIxL0YMsWzQAAAAASUVORK5CYII=","orcid":"","institution":"Anhui Jianzhu University","correspondingAuthor":true,"prefix":"","firstName":"Lili","middleName":"","lastName":"Wang","suffix":""},{"id":310012411,"identity":"2b941c9c-6cb0-4c67-ac0c-425368ffc525","order_by":3,"name":"Yang Zhao","email":"","orcid":"","institution":"Anhui Jianzhu University","correspondingAuthor":false,"prefix":"","firstName":"Yang","middleName":"","lastName":"Zhao","suffix":""},{"id":310012412,"identity":"2db32f86-4507-4c33-98d5-b7cd4d9fc323","order_by":4,"name":"Xu Wang","email":"","orcid":"","institution":"Anhui Jianzhu University","correspondingAuthor":false,"prefix":"","firstName":"Xu","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2024-06-03 08:00:23","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4520181/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4520181/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":68225420,"identity":"f46b8629-f65d-4bec-9bcf-bb4f30c90b5d","added_by":"auto","created_at":"2024-11-05 03:23:20","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2759521,"visible":true,"origin":"","legend":"","description":"","filename":"MultiviewLearningforCamouflagedObjectDetectionwithPVTv2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4520181/v1_covered_9968dacb-cb2d-43b0-802e-b30d97949573.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Multi-view Learning for Camouflaged Object Detection with PVTv2","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"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":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Camouflaged object detection, Multi-view learning, Global context aggregation module, Pyramid vision transformer","lastPublishedDoi":"10.21203/rs.3.rs-4520181/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4520181/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Recently, with the continuous development in the field of camouflage object detection(COD), effectively separating objects highly similar to the background has become a focal point of research. Due to the high similarity between camouflage objects and backgrounds, traditional single visual branch often perform poorly in such scenarios. To address this issue, We propose a multi-view learning detection network based on the Pyramid Vision Transformer, named Multi-view Learning for Camouflaged Object Detection with PVTv2(MVLNet). By utilizing the information from RGB and noise views, our method can provide a more comprehensive description of the relationship between objects and backgrounds to improve the accuracy and robustness for COD. Inspired by human visual attention during observation, we design a Global Context Aggregation Module by using a U-shaped structure and progressively increasing dilation rates to simulate the human behavior of zooming in and out. Extensive experiments demonstrate that the proposed MVLNet outperforms 22 other representative models on three public datasets.","manuscriptTitle":"Multi-view Learning for Camouflaged Object Detection with PVTv2","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-06-17 17:45:20","doi":"10.21203/rs.3.rs-4520181/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"19302095-6367-423f-92e0-8bbd6670f89d","owner":[],"postedDate":"June 17th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-12-16T12:23:37+00:00","versionOfRecord":[],"versionCreatedAt":"2024-06-17 17:45:20","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4520181","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4520181","identity":"rs-4520181","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}