{"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/discovering-class-specific-pixels-for-weakly","title":"Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation","arxiv_id":"1707.05821","date":"2017-07-18","proceeding":null,"authors":["Arslan Chaudhry","Puneet K. Dokania","Philip H. S. Torr"],"abstract":"We propose an approach to discover class-specific pixels for the\nweakly-supervised semantic segmentation task. We show that properly combining\nsaliency and attention maps allows us to obtain reliable cues capable of\nsignificantly boosting the performance. First, we propose a simple yet powerful\nhierarchical approach to discover the class-agnostic salient regions, obtained\nusing a salient object detector, which otherwise would be ignored. Second, we\nuse fully convolutional attention maps to reliably localize the class-specific\nregions in a given image. We combine these two cues to discover class-specific\npixels which are then used as an approximate ground truth for training a CNN.\nWhile solving the weakly supervised semantic segmentation task, we ensure that\nthe image-level classification task is also solved in order to enforce the CNN\nto assign at least one pixel to each object present in the image.\nExperimentally, on the PASCAL VOC12 val and test sets, we obtain the mIoU of\n60.8% and 61.9%, achieving the performance gains of 5.1% and 5.2% compared to\nthe published state-of-the-art results. The code is made publicly available.","url_abs":"http://arxiv.org/abs/1707.05821v1","url_pdf":"http://arxiv.org/pdf/1707.05821v1.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":"discovering-class-specific-pixels-for-weakly","repo_url":"https://github.com/arslan-chaudhry/dcsp_segmentation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"discovering-class-specific-pixels-for-weakly","repo_url":"https://github.com/pramodith/Segmentation-using-Weak-Superivison","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"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=1707.05821","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}