Unsupervised Domain Adaptation for Occlusion Resilient Human Pose Estimation

TL;DR

This paper introduces OR-POSE, an unsupervised domain adaptation method that improves occlusion-resilient human pose estimation by using a mean teacher framework, pose priors, and curriculum learning to handle occlusions and domain shifts.

Contribution

The paper presents OR-POSE, a novel unsupervised domain adaptation algorithm that enhances occlusion robustness in human pose estimation through iterative pseudo-label refinement and a visibility-based curriculum.

Findings

Outperforms state-of-the-art methods by approximately 7% on occluded pose datasets.

Effectively mitigates domain shifts and occlusion challenges in pose estimation.

Utilizes pose priors and curriculum learning to improve prediction accuracy under occlusion.

Abstract

Occlusions are a significant challenge to human pose estimation algorithms, often resulting in inaccurate and anatomically implausible poses. Although current occlusion-robust human pose estimation algorithms exhibit impressive performance on existing datasets, their success is largely attributed to supervised training and the availability of additional information, such as multiple views or temporal continuity. Furthermore, these algorithms typically suffer from performance degradation under distribution shifts. While existing domain adaptive human pose estimation algorithms address this bottleneck, they tend to perform suboptimally when the target domain images are occluded, a common occurrence in real-life scenarios. To address these challenges, we propose OR-POSE: Unsupervised Domain Adaptation for Occlusion Resilient Human POSE Estimation. OR-POSE is an innovative unsupervised domain adaptation algorithm which effectively mitigates domain shifts and overcomes occlusion challenges by employing the mean teacher framework for iterative pseudo-label refinement. Additionally, OR-POSE reinforces realistic pose prediction by leveraging a learned human pose prior which incorporates the anatomical constraints of humans in the adaptation process. Lastly, OR-POSE avoids overfitting to inaccurate pseudo labels generated from heavily occluded images by employing a novel visibility-based curriculum learning approach. This enables the model to gradually transition from training samples with relatively less occlusion to more challenging, heavily occluded samples. Extensive experiments show that OR-POSE outperforms existing analogous state-of-the-art algorithms by $\sim$ 7% on challenging occluded human pose estimation datasets.