Prior-guided Source-free Domain Adaptation for Human Pose Estimation

TL;DR

This paper introduces POST, a source-free domain adaptation method for 2D human pose estimation that uses human pose priors and self-training to improve accuracy without access to source data.

Contribution

It extends source-free domain adaptation techniques to the regression task of pose estimation by incorporating human pose priors into a self-training framework.

Findings

Significant performance improvements over direct application of source model

Achieves comparable results to state-of-the-art methods using source data

Effective use of pose priors for regularization during adaptation

Abstract

Domain adaptation methods for 2D human pose estimation typically require continuous access to the source data during adaptation, which can be challenging due to privacy, memory, or computational constraints. To address this limitation, we focus on the task of source-free domain adaptation for pose estimation, where a source model must adapt to a new target domain using only unlabeled target data. Although recent advances have introduced source-free methods for classification tasks, extending them to the regression task of pose estimation is non-trivial. In this paper, we present Prior-guided Self-training (POST), a pseudo-labeling approach that builds on the popular Mean Teacher framework to compensate for the distribution shift. POST leverages prediction-level and feature-level consistency between a student and teacher model against certain image transformations. In the absence of source data, POST utilizes a human pose prior that regularizes the adaptation process by directing the model to generate more accurate and anatomically plausible pose pseudo-labels. Despite being simple and intuitive, our framework can deliver significant performance gains compared to applying the source model directly to the target data, as demonstrated in our extensive experiments and ablation studies. In fact, our approach achieves comparable performance to recent state-of-the-art methods that use source data for adaptation.