{"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/pushing-the-envelope-for-depth-based-semi","title":"Pushing the Envelope for Depth-Based Semi-Supervised 3D Hand Pose Estimation with Consistency Training","arxiv_id":"2303.15147","date":"2023-03-27","proceeding":null,"authors":["Mohammad Rezaei","Farnaz Farahanipad","Alex Dillhoff","Vassilis Athitsos"],"abstract":"Despite the significant progress that depth-based 3D hand pose estimation methods have made in recent years, they still require a large amount of labeled training data to achieve high accuracy. However, collecting such data is both costly and time-consuming. To tackle this issue, we propose a semi-supervised method to significantly reduce the dependence on labeled training data. The proposed method consists of two identical networks trained jointly: a teacher network and a student network. The teacher network is trained using both the available labeled and unlabeled samples. It leverages the unlabeled samples via a loss formulation that encourages estimation equivariance under a set of affine transformations. The student network is trained using the unlabeled samples with their pseudo-labels provided by the teacher network. For inference at test time, only the student network is used. Extensive experiments demonstrate that the proposed method outperforms the state-of-the-art semi-supervised methods by large margins.","url_abs":"https://arxiv.org/abs/2303.15147v1","url_pdf":"https://arxiv.org/pdf/2303.15147v1.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":"3d-hand-pose-estimation","task_name":"3D Hand Pose Estimation"},{"task_slug":"hand-pose-estimation","task_name":"Hand Pose Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/hand-pose-estimation-on-icvl-hands","task":"Hand Pose Estimation","dataset":"ICVL Hands","model":"Teacher-Student","rank_in_archive_order":6,"of":15,"metrics":{"Average 3D Error":"5.99"},"uses_additional_data":false},{"leaderboard":"/sota/hand-pose-estimation-on-msra-hands","task":"Hand Pose Estimation","dataset":"MSRA Hands","model":"Teacher-Student","rank_in_archive_order":3,"of":11,"metrics":{"Average 3D Error":"7.18"},"uses_additional_data":false},{"leaderboard":"/sota/hand-pose-estimation-on-nyu-hands","task":"Hand Pose Estimation","dataset":"NYU Hands","model":"Teacher-Student","rank_in_archive_order":5,"of":17,"metrics":{"Average 3D Error":"8.01"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}