A Cascaded Group Attention Mechanism-based Object Detection Algorithm for Construction and Demolition Waste

A Cascaded Group Attention Mechanism-based Object Detection Algorithm for Construction and Demolition Waste | 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 A Cascaded Group Attention Mechanism-based Object Detection Algorithm for Construction and Demolition Waste Zeping Jiang, Ying Yang, Jiayi Hu, Chuyan Yuan This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8211430/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 02 Mar, 2026 Read the published version in Scientific Reports → Version 1 posted 10 You are reading this latest preprint version Abstract Accurate object detection is crucial for managing construction and demolition waste (CDW). However, existing deep-learning models often exhibit limited performance in detecting small objects within complex environments. This study proposes a YOLOv11-based detection algorithm integrated with a novel Cascaded Group Attention (CGA) mechanism to enhance the model’s ability to capture fine-grained features. First, we propose a transformer backbone based on CGA to improve long-range dependency modeling while substantially reducing redundant computations. Second, we employ a bidirectional multi-scale interaction module in the neck to integrate fine-grained details from high-resolution features with semantic context from low-resolution features, enabling accurate detection of CDW objects across scales. Finally, the proposed method is evaluated on two datasets. For comparison, we have reproduced several similar YOLOv11-based algorithms to validate the effectiveness of our approach. The results demonstrate a clear advantage of our approach, achieving mAP scores of 0.938 and 0.962, respectively, thereby surpassing the current state-of-the-art methods. Additionally, visualization of prediction results on test samples further confirms the high accuracy of our model. Physical sciences/Engineering Physical sciences/Mathematics and computing Deep-Learning Object Detection CDW Attention Yolov11 Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 02 Mar, 2026 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 13 Jan, 2026 Reviews received at journal 11 Jan, 2026 Reviewers agreed at journal 10 Jan, 2026 Reviews received at journal 05 Jan, 2026 Reviewers agreed at journal 05 Jan, 2026 Reviewers invited by journal 03 Dec, 2025 Editor assigned by journal 02 Dec, 2025 Editor invited by journal 02 Dec, 2025 Submission checks completed at journal 01 Dec, 2025 First submitted to journal 01 Dec, 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-8211430","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":554990329,"identity":"9887a999-2664-4a70-98d5-39b5ee1d5e00","order_by":0,"name":"Zeping Jiang","email":"","orcid":"","institution":"Changsha University of Science \u0026 Technology","correspondingAuthor":false,"prefix":"","firstName":"Zeping","middleName":"","lastName":"Jiang","suffix":""},{"id":554990330,"identity":"6e4b0b7e-20f9-4113-ac52-32ee4c9ff966","order_by":1,"name":"Ying Yang","email":"data:image/png;base64,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","orcid":"","institution":"Changsha University of Science \u0026 Technology","correspondingAuthor":true,"prefix":"","firstName":"Ying","middleName":"","lastName":"Yang","suffix":""},{"id":554990331,"identity":"2960c15e-a811-4b77-998b-f7bcd9ed8e6a","order_by":2,"name":"Jiayi Hu","email":"","orcid":"","institution":"Changsha University of Science \u0026 Technology","correspondingAuthor":false,"prefix":"","firstName":"Jiayi","middleName":"","lastName":"Hu","suffix":""},{"id":554990332,"identity":"2db62fea-2bfc-4cf2-bce3-2b4303e07c9d","order_by":3,"name":"Chuyan Yuan","email":"","orcid":"","institution":"Changsha University of Science \u0026 Technology","correspondingAuthor":false,"prefix":"","firstName":"Chuyan","middleName":"","lastName":"Yuan","suffix":""}],"badges":[],"createdAt":"2025-11-26 09:53:32","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8211430/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8211430/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-026-41557-5","type":"published","date":"2026-03-02T15:56:59+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":97671179,"identity":"58bcb0b7-ddef-4e25-b538-ba695e6575aa","added_by":"auto","created_at":"2025-12-08 09:32:05","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":885131,"visible":true,"origin":"","legend":"","description":"","filename":"ACascadedGroupAttentionMechanismbasedObjectDetectionAlgorithmforConstructionandDemolitionWaste.docx","url":"https://assets-eu.researchsquare.com/files/rs-8211430/v1/b154abafc3291465600384df.docx"},{"id":97544818,"identity":"b4ad3ed2-a6fc-4f73-b319-385cd9b96614","added_by":"auto","created_at":"2025-12-05 15:48:08","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5487,"visible":true,"origin":"","legend":"","description":"","filename":"49ceadf414154fea8fd85bef96aef741.json","url":"https://assets-eu.researchsquare.com/files/rs-8211430/v1/132e699300901a0cc3600be7.json"},{"id":97544819,"identity":"7708b2a8-a68c-4fc2-84ac-735c3b4eb424","added_by":"auto","created_at":"2025-12-05 15:48:08","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":126630,"visible":true,"origin":"","legend":"","description":"","filename":"49ceadf414154fea8fd85bef96aef7411enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8211430/v1/61b8870d2e383a007ceaf553.xml"},{"id":97672806,"identity":"ab7642ec-1da4-407a-af04-fdf783897929","added_by":"auto","created_at":"2025-12-08 09:38:50","extension":"jpeg","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":100131,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8211430/v1/2c816d54f4d3d3dbc5839350.jpeg"},{"id":97544820,"identity":"6eb2bd11-bef4-4acd-8d8a-2acf96df9653","added_by":"auto","created_at":"2025-12-05 15:48:08","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":162894,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8211430/v1/a9336367aa483f86d4f68c6e.png"},{"id":97544821,"identity":"5fcf3384-c39e-402c-8b7b-487eaecdd0a1","added_by":"auto","created_at":"2025-12-05 15:48:08","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":185847,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8211430/v1/639336af434337753df623b7.png"},{"id":97544822,"identity":"25ba43b4-4d8d-40de-b409-2d5215a40cf6","added_by":"auto","created_at":"2025-12-05 15:48:08","extension":"jpeg","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":140982,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8211430/v1/4a5ed0b0f33fc49c91d8af5b.jpeg"},{"id":97544827,"identity":"e571db56-be2f-46c4-9f31-7eec9b688b2f","added_by":"auto","created_at":"2025-12-05 15:48:09","extension":"jpeg","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":180876,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8211430/v1/c6315bb48a29f12e277c917f.jpeg"},{"id":97672821,"identity":"15872054-b624-4c01-b672-9e83ea220979","added_by":"auto","created_at":"2025-12-08 09:38:51","extension":"jpeg","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":428612,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8211430/v1/8f6a70daf38988055c4dae31.jpeg"},{"id":97544824,"identity":"c5aab0e2-b2a6-4155-818e-0aa1e1eda0a3","added_by":"auto","created_at":"2025-12-05 15:48:08","extension":"jpeg","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":712237,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8211430/v1/df569c8782cc3e1616f5a24e.jpeg"},{"id":97671155,"identity":"25481d15-7482-4d47-a534-2b913798eb1e","added_by":"auto","created_at":"2025-12-08 09:32:01","extension":"jpeg","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":494527,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage8.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8211430/v1/7f7ed7685f1bbbf0059fdb18.jpeg"},{"id":97544825,"identity":"154e96bd-957c-46d2-b37a-0031d964f3d6","added_by":"auto","created_at":"2025-12-05 15:48:08","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":74212,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8211430/v1/408d43549f24db1be253ab08.png"},{"id":97544834,"identity":"89232d42-0f4e-4265-a7db-ca84ed32d7d0","added_by":"auto","created_at":"2025-12-05 15:48:09","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":50511,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8211430/v1/64cbadc963512c877000bb86.png"},{"id":97544831,"identity":"4c90a937-29b7-4561-9804-cbac7c828b4e","added_by":"auto","created_at":"2025-12-05 15:48:09","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":56483,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8211430/v1/b724185d44821b3a643bab51.png"},{"id":97672239,"identity":"7d6eeba4-ad06-48f2-8890-f49fabdf84ea","added_by":"auto","created_at":"2025-12-08 09:34:55","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":32368,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8211430/v1/2f339a515b69884ee3d855a5.png"},{"id":97544835,"identity":"7782734f-5c6c-4605-8f8f-18c095c1d7b8","added_by":"auto","created_at":"2025-12-05 15:48:09","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":34585,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-8211430/v1/ddef317f8b796b08e31bf421.png"},{"id":97544830,"identity":"e4f9bd69-44ac-4f05-a229-fa532cb50ea6","added_by":"auto","created_at":"2025-12-05 15:48:09","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":105334,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-8211430/v1/0fd590ffde08ed1e3d37d223.png"},{"id":97544837,"identity":"0399df2c-6538-4d2b-aec5-caaaa7ec974a","added_by":"auto","created_at":"2025-12-05 15:48:09","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":298302,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-8211430/v1/d408e88f14df209c0a616d04.png"},{"id":97544838,"identity":"151c45fd-ed72-4999-a9a6-9da659225114","added_by":"auto","created_at":"2025-12-05 15:48:09","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":174176,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-8211430/v1/dbf052028c39ea6e205e188b.png"},{"id":97544836,"identity":"aad679e0-0856-4eb1-9899-468c687bf2a7","added_by":"auto","created_at":"2025-12-05 15:48:09","extension":"xml","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":125811,"visible":true,"origin":"","legend":"","description":"","filename":"49ceadf414154fea8fd85bef96aef7411structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8211430/v1/f82ffb5d4a9dd45d572c38ba.xml"},{"id":97544839,"identity":"a0878449-85bd-49f5-9764-331094d44bb0","added_by":"auto","created_at":"2025-12-05 15:48:09","extension":"html","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":142749,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8211430/v1/88cea6e9e43bedb57d7a4c57.html"},{"id":104250907,"identity":"e4a5c76a-a0bd-4f39-80ff-608700933fdd","added_by":"auto","created_at":"2026-03-09 16:11:25","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1040392,"visible":true,"origin":"","legend":"","description":"","filename":"ACascadedGroupAttentionMechanismbasedObjectDetectionAlgorithmforConstructionandDemolitionWaste.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8211430/v1_covered_65593449-e4b7-4100-a141-f577592f091e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Cascaded Group Attention Mechanism-based Object Detection Algorithm for Construction and Demolition Waste","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":"Deep-Learning, Object Detection, CDW, Attention, Yolov11","lastPublishedDoi":"10.21203/rs.3.rs-8211430/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8211430/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAccurate object detection is crucial for managing construction and demolition waste (CDW). However, existing deep-learning models often exhibit limited performance in detecting small objects within complex environments. This study proposes a YOLOv11-based detection algorithm integrated with a novel Cascaded Group Attention (CGA) mechanism to enhance the model\u0026rsquo;s ability to capture fine-grained features. First, we propose a transformer backbone based on CGA to improve long-range dependency modeling while substantially reducing redundant computations. Second, we employ a bidirectional multi-scale interaction module in the neck to integrate fine-grained details from high-resolution features with semantic context from low-resolution features, enabling accurate detection of CDW objects across scales. Finally, the proposed method is evaluated on two datasets. For comparison, we have reproduced several similar YOLOv11-based algorithms to validate the effectiveness of our approach. The results demonstrate a clear advantage of our approach, achieving mAP scores of 0.938 and 0.962, respectively, thereby surpassing the current state-of-the-art methods. Additionally, visualization of prediction results on test samples further confirms the high accuracy of our model.\u003c/p\u003e","manuscriptTitle":"A Cascaded Group Attention Mechanism-based Object Detection Algorithm for Construction and Demolition Waste","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-05 15:48:04","doi":"10.21203/rs.3.rs-8211430/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-01-13T16:00:54+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-12T02:51:49+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"269336253477916403817894815182197945777","date":"2026-01-11T01:45:53+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-06T04:13:56+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"62098894549797738476621933981272029788","date":"2026-01-05T14:46:12+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-12-03T18:51:00+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-12-02T19:34:10+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-12-02T18:16:31+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-12-01T15:41:14+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-12-01T15:05:17+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":"f71475f2-6d66-45f1-a10b-70c2c00a718f","owner":[],"postedDate":"December 5th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":59062698,"name":"Physical sciences/Engineering"},{"id":59062699,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-03-09T16:07:59+00:00","versionOfRecord":{"articleIdentity":"rs-8211430","link":"https://doi.org/10.1038/s41598-026-41557-5","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2026-03-02 15:56:59","publishedOnDateReadable":"March 2nd, 2026"},"versionCreatedAt":"2025-12-05 15:48:04","video":"","vorDoi":"10.1038/s41598-026-41557-5","vorDoiUrl":"https://doi.org/10.1038/s41598-026-41557-5","workflowStages":[]},"version":"v1","identity":"rs-8211430","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8211430","identity":"rs-8211430","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}