{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/convolutional-simplex-projection-network-cspn","title":"Convolutional Simplex Projection Network (CSPN) for Weakly Supervised Semantic Segmentation","arxiv_id":"1807.09169","date":"2018-07-24","proceeding":null,"authors":["Rania Briq","Michael Moeller","Juergen Gall"],"abstract":"Weakly supervised semantic segmentation has been a subject of increased\ninterest due to the scarcity of fully annotated images. We introduce a new\napproach for solving weakly supervised semantic segmentation with deep\nConvolutional Neural Networks (CNNs). The method introduces a novel layer which\napplies simplex projection on the output of a neural network using area\nconstraints of class objects. The proposed method is general and can be\nseamlessly integrated into any CNN architecture. Moreover, the projection layer\nallows strongly supervised models to be adapted to weakly supervised models\neffortlessly by substituting ground truth labels. Our experiments have shown\nthat applying such an operation on the output of a CNN improves the accuracy of\nsemantic segmentation in a weakly supervised setting with image-level labels.","url_abs":"http://arxiv.org/abs/1807.09169v1","url_pdf":"http://arxiv.org/pdf/1807.09169v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"convolutional-simplex-projection-network-cspn","repo_url":"https://github.com/briqr/CSPN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"caffe2","reach":null}],"tasks":[{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"weakly-supervised-semantic-segmentation-1","task_name":"Weakly supervised Semantic Segmentation"},{"task_slug":"weakly-supervised-semantic-segmentation","task_name":"Weakly-Supervised Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.09169","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}