Rethinking on Multi-Stage Networks for Human Pose Estimation
arXiv:1901.00148
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.
References in corpus (6)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Human Pose Regression by Combining Indirect Part Detection and Contextual Information
- Multi-Context Attention for Human Pose Estimation
- Human Pose Estimation with Spatial Contextual Information
- Deep High-Resolution Representation Learning for Human Pose Estimation
- Self Adversarial Training for Human Pose Estimation