Rethinking on Multi-Stage Networks for Human Pose Estimation

Code

• github.com/megvii-detection/MSPN
  OfficialIn paperpytorch★ 0
• github.com/open-mmlab/mmpose
  pytorch★ 7,439
• github.com/chenyilun95/tf-cpn
  tf★ 795
• github.com/hyperionfalling/lightpose
  pytorch★ 0
• github.com/yangyucheng000/MSPN
  mindspore★ 0
• github.com/xiuyu0000/papers_with_examples/tree/main/mspn
  mindspore★ 0
• github.com/fenglinglwb/MSPN
  pytorch★ 0

Abstract

Existing pose estimation approaches fall into two categories: single-stage and multi-stage methods. While multi-stage methods are seemingly more suited for the task, their performance in current practice is not as good as single-stage methods. This work studies this issue. We argue that the current multi-stage methods' unsatisfactory performance comes from the insufficiency in various design choices. We propose several improvements, including the single-stage module design, cross stage feature aggregation, and coarse-to-fine supervision. The resulting method establishes the new state-of-the-art on both MS COCO and MPII Human Pose dataset, justifying the effectiveness of a multi-stage architecture. The source code is publicly available for further research.

Tasks

Benchmark Results

Reproductions