Deep High-Resolution Network with Double Attention Residual Blocks for Human Pose Estimation

Abstract

To improve the accuracy of human pose estimation, a novel method based on the deep high-resolution network (HRNet) and equipped with double attention residual blocks is proposed. Firstly, the channel attention and spatial attention modules are added to the residual block of feature extraction, resulting in the network paying more attention to the target area which needs to be extracted important information and suppressed unimportant information. Moreover, this paper proposes a novel module, Parallel Residual Attention Block (PRAB), which parallels the $3\times 3$ group convolution of ResNeXt to the $3\times 3$ convolution layer in the Bottleneck of ResNet, and then adds channel attention and spatial attention modules to these two branches respectively. In this way, the network can further improve the accuracy of human keypoint detection without significantly increasing the computation overhead. To demonstrate the effectiveness of our method, a series of comparative experiments are conducted on the MPII Human Pose dataset and the COCO2017 keypoint detection dataset. Experimental results illustrate that the attention mechanism is effective to improve the accuracy of human pose estimation and the proposed PRAB obtained the best results 90.5% on MPII which outperforms the existing methods.