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

by   Dripta S. Raychaudhuri, et al.

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.


page 1

page 4

page 7

page 8

page 12


Anatomy-guided domain adaptation for 3D in-bed human pose estimation

3D human pose estimation is a key component of clinical monitoring syste...

Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimation

The advances in monocular 3D human pose estimation are dominated by supe...

Spacecraft Pose Estimation Based on Unsupervised Domain Adaptation and on a 3D-Guided Loss Combination

Spacecraft pose estimation is a key task to enable space missions in whi...

Adapted Human Pose: Monocular 3D Human Pose Estimation with Zero Real 3D Pose Data

The ultimate goal for an inference model is to be robust and functional ...

Global Adaptation meets Local Generalization: Unsupervised Domain Adaptation for 3D Human Pose Estimation

When applying a pre-trained 2D-to-3D human pose lifting model to a targe...

Aligning Silhouette Topology for Self-Adaptive 3D Human Pose Recovery

Articulation-centric 2D/3D pose supervision forms the core training obje...

SimPose: Effectively Learning DensePose and Surface Normals of People from Simulated Data

With a proliferation of generic domain-adaptation approaches, we report ...

Please sign up or login with your details

Forgot password? Click here to reset