{"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/causal-intervention-for-weakly-supervised","title":"Causal Intervention for Weakly-Supervised Semantic Segmentation","arxiv_id":"2009.12547","date":"2020-09-26","proceeding":"NeurIPS 2020 12","authors":["Dong Zhang","Hanwang Zhang","Jinhui Tang","Xian-Sheng Hua","Qianru Sun"],"abstract":"We present a causal inference framework to improve Weakly-Supervised Semantic Segmentation (WSSS). Specifically, we aim to generate better pixel-level pseudo-masks by using only image-level labels -- the most crucial step in WSSS. We attribute the cause of the ambiguous boundaries of pseudo-masks to the confounding context, e.g., the correct image-level classification of \"horse\" and \"person\" may be not only due to the recognition of each instance, but also their co-occurrence context, making the model inspection (e.g., CAM) hard to distinguish between the boundaries. Inspired by this, we propose a structural causal model to analyze the causalities among images, contexts, and class labels. Based on it, we develop a new method: Context Adjustment (CONTA), to remove the confounding bias in image-level classification and thus provide better pseudo-masks as ground-truth for the subsequent segmentation model. On PASCAL VOC 2012 and MS-COCO, we show that CONTA boosts various popular WSSS methods to new state-of-the-arts.","url_abs":"https://arxiv.org/abs/2009.12547v2","url_pdf":"https://arxiv.org/pdf/2009.12547v2.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":"attribute","task_name":"Attribute"},{"task_slug":"causal-inference","task_name":"Causal Inference"},{"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":[{"method_slug":"causal-inference","method_name":"Causal inference"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on-4","task":"Weakly-Supervised Semantic Segmentation","dataset":"COCO 2014 val","model":"IRNet+CONTA","rank_in_archive_order":37,"of":39,"metrics":{"mIoU":"33.4"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on","task":"Weakly-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 val","model":"SEAM+CONTA","rank_in_archive_order":69,"of":73,"metrics":{"Mean IoU":"66.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2009.12547","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}