A New Teacher-Reviewer-Student Framework for Semi-supervised 2D Human Pose Estimation

TL;DR

This paper introduces a novel semi-supervised 2D human pose estimation framework that leverages a teacher-reviewer-student architecture, multi-level feature learning, and data augmentation to improve accuracy with limited labeled data.

Contribution

The paper proposes a new teacher-reviewer-student framework, multi-level feature learning, and Keypoint-Mix data augmentation for semi-supervised 2D human pose estimation, addressing limitations of previous methods.

Findings

Significant performance improvements over existing methods.

Effective utilization of unlabeled data through the proposed framework.

Enhanced keypoint detection accuracy with the new strategies.

Abstract

Conventional 2D human pose estimation methods typically require extensive labeled annotations, which are both labor-intensive and expensive. In contrast, semi-supervised 2D human pose estimation can alleviate the above problems by leveraging a large amount of unlabeled data along with a small portion of labeled data. Existing semi-supervised 2D human pose estimation methods update the network through backpropagation, ignoring crucial historical information from the previous training process. Therefore, we propose a novel semi-supervised 2D human pose estimation method by utilizing a newly designed Teacher-Reviewer-Student framework. Specifically, we first mimic the phenomenon that human beings constantly review previous knowledge for consolidation to design our framework, in which the teacher predicts results to guide the student's learning and the reviewer stores important historical parameters to provide additional supervision signals. Secondly, we introduce a Multi-level Feature Learning strategy, which utilizes the outputs from different stages of the backbone to estimate the heatmap to guide network training, enriching the supervisory information while effectively capturing keypoint relationships. Finally, we design a data augmentation strategy, i.e., Keypoint-Mix, to perturb pose information by mixing different keypoints, thus enhancing the network's ability to discern keypoints. Extensive experiments on publicly available datasets, demonstrate our method achieves significant improvements compared to the existing methods.