Enhancing Weakly Supervised Semantic Segmentation through Multi-Class Token Attention Learning

Enhancing Weakly Supervised Semantic Segmentation through Multi-Class Token Attention 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 Research Article Enhancing Weakly Supervised Semantic Segmentation through Multi-Class Token Attention Learning Huilan Luo, Zhen Zeng This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4716623/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 Weakly supervised semantic segmentation (WSSS) using image-level class labels is challenging due to the limitations of Class Activation Maps (CAMs) in convolutional neural networks (CNNs), which often highlight only the most discriminative image regions. We propose the Hierarchical Multi-Class Token Attention Network (HMCTANet), a novel approach leveraging a Conformer backbone that integrates CNN and Transformer branches. HMCTANet enhances CAMs through multi-class token attention and a Class-Aware Training (CAT) strategy that aligns class tokens with ground-truth labels. Additionally, we introduce a Class Token Regularization Module (CTRM) to improve the discriminative power of class tokens. Our Refinement Module (RM) further refines segmentation by combining class-specific attention and patch-level affinity from the Transformer branch with the CAMs from the CNN branch. HMCTANet achieves state-of-the-art performance, with mIoU scores of 69.0% and 68.4% on the PASCAL VOC 2012 validation and test sets, respectively, demonstrating the effectiveness of our approach for WSSS tasks. Computer vision Image semantic segmentation Deep learning Weakly supervised learning Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 17 Sep, 2024 Reviews received at journal 15 Sep, 2024 Reviews received at journal 04 Sep, 2024 Reviewers agreed at journal 28 Aug, 2024 Reviewers agreed at journal 27 Aug, 2024 Reviewers agreed at journal 27 Aug, 2024 Reviewers invited by journal 25 Aug, 2024 Editor assigned by journal 11 Jul, 2024 Submission checks completed at journal 11 Jul, 2024 First submitted to journal 10 Jul, 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-4716623","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":329086116,"identity":"70f9784f-70d8-456d-9274-256bde6b6ebb","order_by":0,"name":"Huilan Luo","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA70lEQVRIiWNgGAWjYBACPgYGNgYGAwsGBvaGBKhYAh71DGD1IC0SDAw8B0BKDYjVwgDUIgFWSYwWieRjj3kKJOTNJR88k+b584eBnz3HgOHnDnxa0tKNeQwkDHfOTkg25m0zYJDseWPA2HsGn5YcM2mgFsYNtxMSH/M2GDAY3MgxYGZsI6zFfsPNAwmHef4YMNgTqyVxww2GxMc8bEBbJAhp4XmWJjnHQCJ5w5mEZMO5bcY8EmeeFRzsxaOFnz35mMSbPza2G46fSQMy5OT425M3PviJRwsS4EkAkyDiAFEagCmGWIWjYBSMglEw0gAAsL1FKOMC1qIAAAAASUVORK5CYII=","orcid":"","institution":"Jiangxi University of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Huilan","middleName":"","lastName":"Luo","suffix":""},{"id":329086117,"identity":"40c5bb3d-4ff1-456a-abc7-8052aa9cd292","order_by":1,"name":"Zhen Zeng","email":"","orcid":"","institution":"Jiangxi University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Zhen","middleName":"","lastName":"Zeng","suffix":""}],"badges":[],"createdAt":"2024-07-10 08:24:26","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4716623/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4716623/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":61738171,"identity":"cacb7a89-4cc0-4839-b370-f58c9341a3b1","added_by":"auto","created_at":"2024-08-05 04:00:02","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3741175,"visible":true,"origin":"","legend":"","description":"","filename":"ArticleTitle.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4716623/v1_covered_b9180884-2734-4daa-b504-2b1b0fb6f4a2.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Enhancing Weakly Supervised Semantic Segmentation through Multi-Class Token Attention Learning","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":"the-journal-of-supercomputing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [The Journal of Supercomputing](https://www.springer.com/journal/11227)","snPcode":"11227","submissionUrl":"https://submission.nature.com/new-submission/11227/3","title":"The Journal of Supercomputing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Computer vision, Image semantic segmentation, Deep learning, Weakly supervised learning","lastPublishedDoi":"10.21203/rs.3.rs-4716623/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4716623/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eWeakly supervised semantic segmentation (WSSS) using image-level class labels is challenging due to the limitations of Class Activation Maps (CAMs) in convolutional neural networks (CNNs), which often highlight only the most discriminative image regions. We propose the Hierarchical Multi-Class Token Attention Network (HMCTANet), a novel approach leveraging a Conformer backbone that integrates CNN and Transformer branches. HMCTANet enhances CAMs through multi-class token attention and a Class-Aware Training (CAT) strategy that aligns class tokens with ground-truth labels. Additionally, we introduce a Class Token Regularization Module (CTRM) to improve the discriminative power of class tokens. Our Refinement Module (RM) further refines segmentation by combining class-specific attention and patch-level affinity from the Transformer branch with the CAMs from the CNN branch. HMCTANet achieves state-of-the-art performance, with mIoU scores of 69.0% and 68.4% on the PASCAL VOC 2012 validation and test sets, respectively, demonstrating the effectiveness of our approach for WSSS tasks.\u003c/p\u003e","manuscriptTitle":"Enhancing Weakly Supervised Semantic Segmentation through Multi-Class Token Attention Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-08-05 03:51:49","doi":"10.21203/rs.3.rs-4716623/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-09-17T23:49:06+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-09-15T06:46:04+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-09-04T13:12:44+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"316408966190677311155743472743134448624","date":"2024-08-28T06:41:16+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"199231608562570850378541649367627374103","date":"2024-08-28T02:13:00+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"193909909686555339848484229453970776543","date":"2024-08-28T01:59:32+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-08-25T16:18:00+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-07-11T09:44:58+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-07-11T09:42:18+00:00","index":"","fulltext":""},{"type":"submitted","content":"The Journal of Supercomputing","date":"2024-07-10T08:23:12+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"the-journal-of-supercomputing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [The Journal of Supercomputing](https://www.springer.com/journal/11227)","snPcode":"11227","submissionUrl":"https://submission.nature.com/new-submission/11227/3","title":"The Journal of Supercomputing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"01c436b1-df20-46e3-9ca3-bd75f7140ec3","owner":[],"postedDate":"August 5th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2024-10-14T15:08:39+00:00","versionOfRecord":[],"versionCreatedAt":"2024-08-05 03:51:49","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4716623","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4716623","identity":"rs-4716623","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}