{"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/weakly-and-semi-supervised-learning-of-a-dcnn","title":"Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation","arxiv_id":"1502.02734","date":"2015-02-09","proceeding":null,"authors":["George Papandreou","Liang-Chieh Chen","Kevin Murphy","Alan L. Yuille"],"abstract":"Deep convolutional neural networks (DCNNs) trained on a large number of\nimages with strong pixel-level annotations have recently significantly pushed\nthe state-of-art in semantic image segmentation. We study the more challenging\nproblem of learning DCNNs for semantic image segmentation from either (1)\nweakly annotated training data such as bounding boxes or image-level labels or\n(2) a combination of few strongly labeled and many weakly labeled images,\nsourced from one or multiple datasets. We develop Expectation-Maximization (EM)\nmethods for semantic image segmentation model training under these weakly\nsupervised and semi-supervised settings. Extensive experimental evaluation\nshows that the proposed techniques can learn models delivering competitive\nresults on the challenging PASCAL VOC 2012 image segmentation benchmark, while\nrequiring significantly less annotation effort. We share source code\nimplementing the proposed system at\nhttps://bitbucket.org/deeplab/deeplab-public.","url_abs":"http://arxiv.org/abs/1502.02734v3","url_pdf":"http://arxiv.org/pdf/1502.02734v3.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":"weakly-and-semi-supervised-learning-of-a-dcnn","repo_url":"https://bitbucket.org/deeplab/deeplab-public","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"weakly-and-semi-supervised-learning-of-a-dcnn","repo_url":"https://github.com/TheLegendAli/DeepLab-Context","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"weakly-and-semi-supervised-learning-of-a-dcnn","repo_url":"https://github.com/open-cv/deeplab-v1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"semi-supervised-semantic-segmentation","task_name":"Semi-Supervised Semantic Segmentation"},{"task_slug":"weakly-supervised-semantic-segmentation","task_name":"Weakly-Supervised Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1502.02734","atlas_url":"https://app.syntology.ai/?focus=1502.02734","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}