A-HRNet: Attention Based High Resolution Network for Human pose estimation
A-HRNet: Attention Based High Resolution Network for Human pose estimation
复制标题
DOI：
10.1109/transai49837.2020.00016
复制
发表时间：
2020-09
期刊：
影响因子：
--
通讯作者：
Ying Li;Chenxi Wang;Yu Cao;Benyuan Liu;Yan Luo;Honggang Zhang
中科院分区：
文献类型：
--
作者：
Ying Li;Chenxi Wang;Yu Cao;Benyuan Liu;Yan Luo;Honggang Zhang
近年来，人体姿态估计因其广泛的应用场景而受到研究界的广泛关注。大多数人体姿态估计的架构都使用多分辨率网络，例如Hourglass、CPN、HRNet等。高分辨率网络（HRNet）是从Hourglass改进的最新SOTA架构。在本文中，我们提出了一种新颖的注意力模块，它利用特殊的通道注意力分支。我们使用这个注意力块作为构建块，并采用 HRNet 的架构来构建我们的基于注意力的 HRNet（A-HRNet）。实验表明，我们的模型在不同数据集上始终优于 HRNet。此外，我们的模型在 COCO 关键点检测 val2017 数据集 (77.7 AP)1 上实现了最先进的性能。
Recently, human pose estimation has received much attention in the research community due to its broad range of application scenarios. Most architectures for human pose estimation use multiple resolution networks, such as Hourglass, CPN, HRNet, etc. High Resolution Network (HRNet) is the latest SOTA architecture improved from Hourglass. In this paper, we propose a novel attention block that leverages a special Channel-Attention branch. We use this attention block as the building block and adopt the architecture of HRNet to build our Attention Based HRNet (A-HRNet). Experiments show that our model can consistently outperform HRNet on different datasets. Moreover, our model achieves the state-of-the-art performance on the COCO keypoint detection val2017 dataset (77.7 AP)1.