{"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/self-adversarial-training-for-human-pose","title":"Self Adversarial Training for Human Pose Estimation","arxiv_id":"1707.02439","date":"2017-07-08","proceeding":null,"authors":["Chia-Jung Chou","Jui-Ting Chien","Hwann-Tzong Chen"],"abstract":"This paper presents a deep learning based approach to the problem of human\npose estimation. We employ generative adversarial networks as our learning\nparadigm in which we set up two stacked hourglass networks with the same\narchitecture, one as the generator and the other as the discriminator. The\ngenerator is used as a human pose estimator after the training is done. The\ndiscriminator distinguishes ground-truth heatmaps from generated ones, and\nback-propagates the adversarial loss to the generator. This process enables the\ngenerator to learn plausible human body configurations and is shown to be\nuseful for improving the prediction accuracy.","url_abs":"http://arxiv.org/abs/1707.02439v2","url_pdf":"http://arxiv.org/pdf/1707.02439v2.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":"self-adversarial-training-for-human-pose","repo_url":"https://github.com/dongzhuoyao/jessiechouuu-adversarial-pose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":null}],"tasks":[{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/pose-estimation-on-leeds-sports-poses","task":"Pose Estimation","dataset":"Leeds Sports Poses","model":"Chou et al. arXiv'17","rank_in_archive_order":5,"of":18,"metrics":{"PCK":"94%"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-mpii-human-pose","task":"Pose Estimation","dataset":"MPII Human Pose","model":"Chou et al. arXiv'17","rank_in_archive_order":16,"of":46,"metrics":{"PCKh-0.5":"91.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.02439","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}