{"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/semantic-image-segmentation-via-deep-parsing","title":"Semantic Image Segmentation via Deep Parsing Network","arxiv_id":"1509.02634","date":"2015-09-09","proceeding":"ICCV 2015 12","authors":["Ziwei Liu","Xiaoxiao Li","Ping Luo","Chen Change Loy","Xiaoou Tang"],"abstract":"This paper addresses semantic image segmentation by incorporating rich\ninformation into Markov Random Field (MRF), including high-order relations and\nmixture of label contexts. Unlike previous works that optimized MRFs using\niterative algorithm, we solve MRF by proposing a Convolutional Neural Network\n(CNN), namely Deep Parsing Network (DPN), which enables deterministic\nend-to-end computation in a single forward pass. Specifically, DPN extends a\ncontemporary CNN architecture to model unary terms and additional layers are\ncarefully devised to approximate the mean field algorithm (MF) for pairwise\nterms. It has several appealing properties. First, different from the recent\nworks that combined CNN and MRF, where many iterations of MF were required for\neach training image during back-propagation, DPN is able to achieve high\nperformance by approximating one iteration of MF. Second, DPN represents\nvarious types of pairwise terms, making many existing works as its special\ncases. Third, DPN makes MF easier to be parallelized and speeded up in\nGraphical Processing Unit (GPU). DPN is thoroughly evaluated on the PASCAL VOC\n2012 dataset, where a single DPN model yields a new state-of-the-art\nsegmentation accuracy.","url_abs":"http://arxiv.org/abs/1509.02634v2","url_pdf":"http://arxiv.org/pdf/1509.02634v2.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":"semantic-image-segmentation-via-deep-parsing","repo_url":"https://github.com/luwill/Semantic-Segmentation-Guide","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok"}}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-cityscapes","task":"Semantic Segmentation","dataset":"Cityscapes test","model":"DPN","rank_in_archive_order":91,"of":105,"metrics":{"Mean IoU (class)":"66.8%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1509.02634","atlas_url":"https://app.syntology.ai/?focus=1509.02634","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}