Improving Robustness for Pose Estimation via Stable Heatmap Regression

TL;DR

This paper introduces a stable heatmap regression method that enhances the robustness of pose estimation models against small perturbations, maintaining high accuracy and outperforming existing approaches on benchmark datasets.

Contribution

The paper proposes a novel heatmap regression technique with correlation-based multi-peak alleviation and stability training to improve robustness in pose estimation.

Findings

Significant robustness improvements over state-of-the-art methods.

Maintains high performance on benchmark datasets.

Effective in reducing keypoint prediction variability.

Abstract

Deep learning methods have achieved excellent performance in pose estimation, but the lack of robustness causes the keypoints to change drastically between similar images. In view of this problem, a stable heatmap regression method is proposed to alleviate network vulnerability to small perturbations. We utilize the correlation between different rows and columns in a heatmap to alleviate the multi-peaks problem, and design a highly differentiated heatmap regression to make a keypoint discriminative from surrounding points. A maximum stability training loss is used to simplify the optimization difficulty when minimizing the prediction gap of two similar images. The proposed method achieves a significant advance in robustness over state-of-the-art approaches on two benchmark datasets and maintains high performance.