A Coarse-to-Fine Human Pose Estimation Method based on Two-stage Distillation and Progressive Graph Neural Network

TL;DR

This paper introduces a two-stage knowledge distillation framework with a progressive graph neural network for lightweight and accurate human pose estimation, improving performance especially on complex datasets.

Contribution

It proposes a novel coarse-to-fine distillation approach utilizing joint structure loss and a progressive GCN, enhancing pose estimation accuracy with fewer resources.

Findings

Outperforms existing methods on COCO and CrowdPose datasets.

Significant performance gains on complex CrowdPose dataset.

Effective transfer of structural and semantic knowledge from teacher to student.

Abstract

Human pose estimation has been widely applied in the human-centric understanding and generation, but most existing state-of-the-art human pose estimation methods require heavy computational resources for accurate predictions. In order to obtain an accurate, robust yet lightweight human pose estimator, one feasible way is to transfer pose knowledge from a powerful teacher model to a less-parameterized student model by knowledge distillation. However, the traditional knowledge distillation framework does not fully explore the contextual information among human joints. Thus, in this paper, we propose a novel coarse-to-fine two-stage knowledge distillation framework for human pose estimation. In the first-stage distillation, we introduce the human joints structure loss to mine the structural information among human joints so as to transfer high-level semantic knowledge from the teacher model to the student model. In the second-stage distillation, we utilize an Image-Guided Progressive Graph Convolutional Network (IGP-GCN) to refine the initial human pose obtained from the first-stage distillation and supervise the training of the IGP-GCN in the progressive way by the final output pose of teacher model. The extensive experiments on the benchmark dataset: COCO keypoint and CrowdPose datasets, show that our proposed method performs favorably against lots of the existing state-of-the-art human pose estimation methods, especially for the more complex CrowdPose dataset, the performance improvement of our model is more significant.