X-HRNet：基于空间一维自注意力机制的轻量级人体姿态估计
X-HRNet: Towards Lightweight Human Pose Estimation with Spatially Unidimensional Self-Attention
AI总结：
提出基于空间一维自注意力（SUSA）的轻量级姿态估计网络X-HRNet，通过降低逐点卷积96%计算量且不损失精度，在COCO基准上验证了其高效性。
摘要：
高分辨率表示对于人体姿态估计达到高性能是必要的，随之而来的问题是高计算复杂度。特别是，主流姿态估计方法通过二维单峰热图来估计人体关节。每个二维热图可以水平或垂直投影，并由一对一维热向量重建。受此观察启发，我们引入了一种轻量且强大的替代方案——空间一维自注意力（SUSA），用于替代逐点（1x1）卷积，而逐点卷积是深度可分离3x3卷积中的主要计算瓶颈。我们的SUSA将逐点（1x1）卷积的计算复杂度降低了96%，且不牺牲精度。此外，我们使用SUSA作为主要模块构建了轻量级姿态估计骨干网络X-HRNet，其中'X'表示估计的交叉形状注意力向量。在COCO基准上的大量实验证明了我们X-HRNet的优越性，全面的消融研究显示了SUSA模块的有效性。代码公开于https://github.com/cool-xuan/x-hrnet。
英文摘要：
High-resolution representation is necessary for human pose estimation to achieve high performance, and the ensuing problem is high computational complexity. In particular, predominant pose estimation methods estimate human joints by 2D single-peak heatmaps. Each 2D heatmap can be horizontally and vertically projected to and reconstructed by a pair of 1D heat vectors. Inspired by this observation, we introduce a lightweight and powerful alternative, Spatially Unidimensional Self-Attention (SUSA), to the pointwise (1x1) convolution that is the main computational bottleneck in the depthwise separable 3c3 convolution. Our SUSA reduces the computational complexity of the pointwise (1x1) convolution by 96% without sacrificing accuracy. Furthermore, we use the SUSA as the main module to build our lightweight pose estimation backbone X-HRNet, where `X' represents the estimated cross-shape attention vectors. Extensive experiments on the COCO benchmark demonstrate the superiority of our X-HRNet, and comprehensive ablation studies show the effectiveness of the SUSA modules. The code is publicly available at https://github.com/cool-xuan/x-hrnet.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
