{"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/uda-cope-unsupervised-domain-adaptation-for","title":"UDA-COPE: Unsupervised Domain Adaptation for Category-level Object Pose Estimation","arxiv_id":"2111.12580","date":"2021-11-24","proceeding":"CVPR 2022 1","authors":["Taeyeop Lee","Byeong-Uk Lee","Inkyu Shin","Jaesung Choe","Ukcheol Shin","In So Kweon","Kuk-Jin Yoon"],"abstract":"Learning to estimate object pose often requires ground-truth (GT) labels, such as CAD model and absolute-scale object pose, which is expensive and laborious to obtain in the real world. To tackle this problem, we propose an unsupervised domain adaptation (UDA) for category-level object pose estimation, called UDA-COPE. Inspired by recent multi-modal UDA techniques, the proposed method exploits a teacher-student self-supervised learning scheme to train a pose estimation network without using target domain pose labels. We also introduce a bidirectional filtering method between the predicted normalized object coordinate space (NOCS) map and observed point cloud, to not only make our teacher network more robust to the target domain but also to provide more reliable pseudo labels for the student network training. Extensive experimental results demonstrate the effectiveness of our proposed method both quantitatively and qualitatively. Notably, without leveraging target-domain GT labels, our proposed method achieved comparable or sometimes superior performance to existing methods that depend on the GT labels.","url_abs":"https://arxiv.org/abs/2111.12580v2","url_pdf":"https://arxiv.org/pdf/2111.12580v2.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":"6d-pose-estimation-using-rgbd","task_name":"6D Pose Estimation using RGBD"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/6d-pose-estimation-using-rgbd-on-real275","task":"6D Pose Estimation using RGBD","dataset":"REAL275","model":"UDA-COPE","rank_in_archive_order":5,"of":11,"metrics":{"mAP 10, 2cm":"56.9","mAP 10, 5cm":"66.0","mAP 3DIou@50":"82.6","mAP 3DIou@75":"62.5","mAP 5, 2cm":"30.4","mAP 5, 5cm":"34.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2111.12580","atlas_url":"https://app.syntology.ai/?focus=2111.12580","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}