论文标题
Dite-hrnet：人姿势估计的动态轻量级高分辨率网络
Dite-HRNet: Dynamic Lightweight High-Resolution Network for Human Pose Estimation
论文作者
论文摘要
高分辨率网络在提取人姿势估计的多尺度特征方面具有显着的能力，但无法捕获关节之间的长距离相互作用，并且具有很高的计算复杂性。为了解决这些问题，我们提出了一个动态的轻质高分辨率网络（Dite-HRNET），该网络可以有效地提取多规模上下文信息，并模拟人体姿势估计的长距离空间依赖性。具体而言，我们提出了两种方法，即动态拆分卷积和自适应上下文建模，并将它们嵌入两个新颖的轻质块中，它们被命名为动态多规模上下文块和动态全局上下文块。作为我们的Dite-HRNET的基本组件单元，这两个块是专门为高分辨率网络设计的，以充分利用并行的多分辨率体系结构。实验结果表明，所提出的网络在可可和MPII人类姿势估计数据集上都能达到卓越的性能，超过了最先进的轻量级网络。代码可在以下网址找到：https：//github.com/ziyizhang27/dite-hrnet。
A high-resolution network exhibits remarkable capability in extracting multi-scale features for human pose estimation, but fails to capture long-range interactions between joints and has high computational complexity. To address these problems, we present a Dynamic lightweight High-Resolution Network (Dite-HRNet), which can efficiently extract multi-scale contextual information and model long-range spatial dependency for human pose estimation. Specifically, we propose two methods, dynamic split convolution and adaptive context modeling, and embed them into two novel lightweight blocks, which are named dynamic multi-scale context block and dynamic global context block. These two blocks, as the basic component units of our Dite-HRNet, are specially designed for the high-resolution networks to make full use of the parallel multi-resolution architecture. Experimental results show that the proposed network achieves superior performance on both COCO and MPII human pose estimation datasets, surpassing the state-of-the-art lightweight networks. Code is available at: https://github.com/ZiyiZhang27/Dite-HRNet.
