Pose-MUM : Reinforcing Key Points Relationship for Semi-Supervised Human Pose Estimation

TL;DR

Pose-MUM introduces a novel semi-supervised human pose estimation method that enhances key point relationship learning through modified augmentation and a stable teacher, achieving superior results on MS-COCO.

Contribution

The paper proposes Pose-MUM, a new augmentation strategy and teacher model for semi-supervised human pose estimation, improving key point relationship modeling and overall accuracy.

Findings

Outperforms previous SSHPE methods on MS-COCO

Enhances key point relationship learning

Utilizes stable EMAN teacher for better pseudo labels

Abstract

A well-designed strong-weak augmentation strategy and the stable teacher to generate reliable pseudo labels are essential in the teacher-student framework of semi-supervised learning (SSL). Considering these in mind, to suit the semi-supervised human pose estimation (SSHPE) task, we propose a novel approach referred to as Pose-MUM that modifies Mix/UnMix (MUM) augmentation. Like MUM in the dense prediction task, the proposed Pose-MUM makes strong-weak augmentation for pose estimation and leads the network to learn the relationship between each human key point much better than the conventional methods by adding the mixing process in intermediate layers in a stochastic manner. In addition, we employ the exponential-moving-average-normalization (EMAN) teacher, which is stable and well-suited to the SSL framework and furthermore boosts the performance. Extensive experiments on MS-COCO dataset show the superiority of our proposed method by consistently improving the performance over the previous methods following SSHPE benchmark.