Context-aware Learning and Background Activation Suppression for Weakly Supervised Semantic Segmentation

Context-aware Learning and Background Activation Suppression for Weakly Supervised Semantic 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 Research Article Context-aware Learning and Background Activation Suppression for Weakly Supervised Semantic Segmentation Aizhong Mi, Xianru Huang, Zhanqiang Huo, Luyao Liu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4907075/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 07 Feb, 2025 Read the published version in Multimedia Systems → Version 1 posted 13 You are reading this latest preprint version Abstract Weakly supervised semantic segmentation (WSSS) using only image-level labels has gradually become an emerging research hotspot in the field of computer vision in recent years due to its low annotation cost. Existing methods rely on Class Activation Maps (CAMs) from specific classification models to locate target regions. However, the classifiers tend to focus on the most discriminative regions of the input image and assign higher weights to these areas, leading to the problem of incomplete CAM target regions. To address this issue, we design a Siamese feature aggregation network, named SFA-Net, which introduces contextual information to activate more complete target regions while suppressing the similarly adjacent background regions. Specifically, the context-aware module in the SFA-Net is consisting of a multi-scale adaptive aggregation sub-module and a contextual linkage sub-module, which can uncover potential target features and identify global target areas. A background activation suppression loss is designed to minimize false activations in the background regions by measuring the similarity between the target object and background regions at the boundary. Extensive experiments on the challenging PASCAL VOC 2012 and COCO 2014 datasets show that our SFA-Net outperforms other state-of-the-art methods. Semantic segmentation Image-level labels Context-aware learning Background activation suppression Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 07 Feb, 2025 Read the published version in Multimedia Systems → Version 1 posted Editorial decision: Revision requested 08 Dec, 2024 Reviews received at journal 30 Nov, 2024 Reviews received at journal 29 Nov, 2024 Reviews received at journal 25 Nov, 2024 Reviewers agreed at journal 15 Nov, 2024 Reviewers agreed at journal 12 Nov, 2024 Reviewers agreed at journal 11 Nov, 2024 Reviewers agreed at journal 10 Nov, 2024 Reviewers agreed at journal 10 Nov, 2024 Reviewers invited by journal 10 Nov, 2024 Editor assigned by journal 13 Sep, 2024 Submission checks completed at journal 14 Aug, 2024 First submitted to journal 13 Aug, 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-4907075","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":340244236,"identity":"33cab9b6-5606-4875-87b9-2d145e3d38d3","order_by":0,"name":"Aizhong Mi","email":"","orcid":"","institution":"Henan Polytechnic University","correspondingAuthor":false,"prefix":"","firstName":"Aizhong","middleName":"","lastName":"Mi","suffix":""},{"id":340244237,"identity":"5d367314-2a68-4c5d-9788-38c052f2f2dd","order_by":1,"name":"Xianru Huang","email":"","orcid":"","institution":"Henan Polytechnic University","correspondingAuthor":false,"prefix":"","firstName":"Xianru","middleName":"","lastName":"Huang","suffix":""},{"id":340244238,"identity":"39de4885-79d1-4f0e-ba0a-c423ebe29546","order_by":2,"name":"Zhanqiang Huo","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAqElEQVRIiWNgGAWjYBACAwYGxscQZgLxWpiNSdbCJk2aFnP+w9uqC3ccZuBnzzFg+LmDCC2WDcfKbs88c5hBsueNAWPvGWIcdrDH7DZv22EGgxs5BsyMbcRoOcxjVgzSYk+8lmM8ZsxgWySI1nKGrVia90w6j8SZZwUHe4nScv7wxs+8O6zl+NuTNz74SYwWkC4GxgYGHhDrAHEaoFpGwSgYBaNgFOAGAMqqMnltkOmsAAAAAElFTkSuQmCC","orcid":"","institution":"Henan Polytechnic University","correspondingAuthor":true,"prefix":"","firstName":"Zhanqiang","middleName":"","lastName":"Huo","suffix":""},{"id":340244239,"identity":"651ce423-87a2-4ad8-9f60-79a9687252fa","order_by":3,"name":"Luyao Liu","email":"","orcid":"","institution":"Henan Polytechnic University","correspondingAuthor":false,"prefix":"","firstName":"Luyao","middleName":"","lastName":"Liu","suffix":""}],"badges":[],"createdAt":"2024-08-13 12:32:36","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4907075/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4907075/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00530-025-01693-w","type":"published","date":"2025-02-07T15:57:23+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":75932358,"identity":"6284bc13-59a9-4fd0-aeda-716f7cdcf14b","added_by":"auto","created_at":"2025-02-10 16:18:52","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":5018872,"visible":true,"origin":"","legend":"","description":"","filename":"ContextawareLearningandBackgroundActivationSuppressionforWeaklySupervisedSemanticSegmentation3.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4907075/v1_covered_7312e005-f1b0-409a-8cbf-974079cd4523.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Context-aware Learning and Background Activation Suppression for Weakly Supervised Semantic 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":"multimedia-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mmsj","sideBox":"Learn more about [Multimedia Systems](http://link.springer.com/journal/530)","snPcode":"530","submissionUrl":"https://submission.nature.com/new-submission/530/3","title":"Multimedia Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Semantic segmentation, Image-level labels, Context-aware learning, Background activation suppression","lastPublishedDoi":"10.21203/rs.3.rs-4907075/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4907075/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Weakly supervised semantic segmentation (WSSS) using only image-level labels has gradually become an emerging research hotspot in the field of computer vision in recent years due to its low annotation cost. Existing methods rely on Class Activation Maps (CAMs) from specific classification models to locate target regions. However, the classifiers tend to focus on the most discriminative regions of the input image and assign higher weights to these areas, leading to the problem of incomplete CAM target regions. To address this issue, we design a Siamese feature aggregation network, named SFA-Net, which introduces contextual information to activate more complete target regions while suppressing the similarly adjacent background regions. Specifically, the context-aware module in the SFA-Net is consisting of a multi-scale adaptive aggregation sub-module and a contextual linkage sub-module, which can uncover potential target features and identify global target areas. A background activation suppression loss is designed to minimize false activations in the background regions by measuring the similarity between the target object and background regions at the boundary. Extensive experiments on the challenging PASCAL VOC 2012 and COCO 2014 datasets show that our SFA-Net outperforms other state-of-the-art methods.","manuscriptTitle":"Context-aware Learning and Background Activation Suppression for Weakly Supervised Semantic Segmentation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-09-11 06:06:49","doi":"10.21203/rs.3.rs-4907075/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-12-08T13:46:40+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-11-30T07:09:04+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-11-29T10:52:32+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-11-25T12:26:26+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"241671524072586884959979488980494456736","date":"2024-11-15T20:55:03+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"215549469873398393316109647841235509047","date":"2024-11-13T01:20:46+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"140262731448423784339121948841935732720","date":"2024-11-12T02:23:43+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"99256847661885004622435419613235959386","date":"2024-11-10T11:58:29+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"310800708953379663804830780298817211917","date":"2024-11-10T10:18:03+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-11-10T09:54:55+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-09-13T09:24:15+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-08-14T12:37:03+00:00","index":"","fulltext":""},{"type":"submitted","content":"Multimedia Systems","date":"2024-08-13T12:31:15+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"multimedia-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mmsj","sideBox":"Learn more about [Multimedia Systems](http://link.springer.com/journal/530)","snPcode":"530","submissionUrl":"https://submission.nature.com/new-submission/530/3","title":"Multimedia Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"d61ada69-b919-4b17-b7a6-de35722f8d8f","owner":[],"postedDate":"September 11th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-02-10T16:01:26+00:00","versionOfRecord":{"articleIdentity":"rs-4907075","link":"https://doi.org/10.1007/s00530-025-01693-w","journal":{"identity":"multimedia-systems","isVorOnly":false,"title":"Multimedia Systems"},"publishedOn":"2025-02-07 15:57:23","publishedOnDateReadable":"February 7th, 2025"},"versionCreatedAt":"2024-09-11 06:06:49","video":"","vorDoi":"10.1007/s00530-025-01693-w","vorDoiUrl":"https://doi.org/10.1007/s00530-025-01693-w","workflowStages":[]},"version":"v1","identity":"rs-4907075","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4907075","identity":"rs-4907075","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}