A Unified Framework for Domain Adaptive Pose Estimation

TL;DR

This paper introduces a unified domain adaptive framework for 2D pose estimation that effectively transfers knowledge from synthetic to real-world data across various tasks and species, achieving state-of-the-art results.

Contribution

It proposes a generalizable method that aligns input and output representations for domain adaptation in pose estimation, applicable to multiple scenarios and unseen domains.

Findings

Outperforms existing methods on human, hand, and animal pose tasks.

Achieves up to 7.4 percentage points improvement.

Effective on unseen domains and objects.

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.