Efficient Human Pose Estimation by Learning Deeply Aggregated Representations
Authors:
- 5 July 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Abstract
In this paper, we propose an efficient human pose estimation network (DANet) by learning deeply aggregated representations. Most existing models explore multi-scale infonnation mainly from features with different spatial sizes. Powerful multi-scale representations usually rely on the cascaded pyramid framework. This framework largely boosts the performance but in the meanwhile makes networks very deep and complex. Instead, we focus on exploiting multi-scale information from layers with different receptive-field sizes and then making full of use this infonnation by improving the fusion method. Specifically, we propose an orthogonal attention block (OAB) and a second-order fusion unit (SFU). The OAB learns multi-scale infonnation from different layers and enhances them by encouraging them to be diverse. The SFU adaptively selects and fuses diverse multi-scale infonnation and suppress the redundant ones. With the help of OAB and SFU, our networks could achieve comparable or even better accuracy with much smaller model complexity. Specifically, our DANet-72 achieves 71.0 in AP score on COCO val2017 with only 1.0G FLOPS. Its speed on a CPU platfonn achieves 58 Persons-Per-Second (PPS).Keywords
Funding Information
- National Key Research and Development Program of China
- Research and Development
This publication has 8 references indexed in Scilit:
- Learning Delicate Local Representations for Multi-person Pose Estimation2020
- Fast Human Pose Estimation2019
- Simple Baselines for Human Pose Estimation and Tracking2018
- Cascaded Pyramid Network for Multi-person Pose Estimation2018
- xUnit: Learning a Spatial Activation Function for Efficient Image Restoration2018
- Learning Feature Pyramids for Human Pose Estimation2017
- Densely Connected Convolutional Networks2017
- Deep Residual Learning for Image Recognition2016