A unified framework for domain adaptive pose estimation
Files
First author draft
Date
2022-10-23
Authors
Kim, Donghyun
Wang, Kaihong
Saenko, K.
Betke, Margrit
Sclaroff, S.
Version
First author draft
OA Version
Citation
D. Kim, K. Wang, K. Saenko, M. Betke, S. Sclaroff. 2022. "A Unified Framework for Domain Adaptive Pose Estimation" Lecture Notes in Artificial Intelligence, Volume 13693, pp.603-620. https://doi.org/10.1007/978-3-031-19827-4_35
Abstract
While pose estimation is an important computer vision task, it requires expensive annotation and suffers from domain shift. In this paper, we investigate the problem of domain adaptive 2D pose estimation that transfers knowledge learned on a synthetic source domain to a target domain without supervision. While several domain adaptive pose estimation models have been proposed recently, they are not generic but only focus on either human pose or animal pose estimation, and thus their effectiveness is somewhat limited to specific scenarios. In this work, we propose a unified framework that generalizes well on various domain adaptive pose estimation problems. We propose to align representations using both input-level and output-level cues (pixels and pose labels, respectively), which facilitates the knowledge transfer from the source domain to the unlabeled target domain. Our experiments show that our method achieves state-of-the-art performance under various domain shifts. Our method outperforms existing baselines on human pose estimation by up to 4.5 percent points (pp), hand pose estimation by up to 7.4 pp, and animal pose estimation by up to 4.8 pp for dogs and 3.3 pp for sheep. These results suggest that our method is able to mitigate domain shift on diverse tasks and even unseen domains and objects (e.g., trained on horse and tested on dog). Our code will be publicly available at: https://github.com/VisionLearningGroup/UDA_PoseEstimation.