{"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/exploiting-saliency-for-object-segmentation","title":"Exploiting saliency for object segmentation from image level labels","arxiv_id":"1701.08261","date":"2017-01-28","proceeding":"CVPR 2017 7","authors":["Seong Joon Oh","Rodrigo Benenson","Anna Khoreva","Zeynep Akata","Mario Fritz","Bernt Schiele"],"abstract":"There have been remarkable improvements in the semantic labelling task in the\nrecent years. However, the state of the art methods rely on large-scale\npixel-level annotations. This paper studies the problem of training a\npixel-wise semantic labeller network from image-level annotations of the\npresent object classes. Recently, it has been shown that high quality seeds\nindicating discriminative object regions can be obtained from image-level\nlabels. Without additional information, obtaining the full extent of the object\nis an inherently ill-posed problem due to co-occurrences. We propose using a\nsaliency model as additional information and hereby exploit prior knowledge on\nthe object extent and image statistics. We show how to combine both information\nsources in order to recover 80% of the fully supervised performance - which is\nthe new state of the art in weakly supervised training for pixel-wise semantic\nlabelling. The code is available at https://goo.gl/KygSeb.","url_abs":"http://arxiv.org/abs/1701.08261v2","url_pdf":"http://arxiv.org/pdf/1701.08261v2.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":[],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-pascal-voc-2012","task":"Semantic Segmentation","dataset":"PASCAL VOC 2012 test","model":"G2","rank_in_archive_order":50,"of":51,"metrics":{"Mean IoU":"56.7%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-pascal-voc-2012-val","task":"Semantic Segmentation","dataset":"PASCAL VOC 2012 val","model":"G2","rank_in_archive_order":26,"of":29,"metrics":{"mIoU":"55.7%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1701.08261","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}