论文标题
轻巧的人姿势估计使用热图加权损失
Lightweight Human Pose Estimation Using Heatmap-Weighting Loss
论文作者
论文摘要
对人类姿势估计的最新研究利用了复杂的结构，以提高基准数据集的性能，而忽略了模型实际部署时的资源开销和推理速度。在本文中，我们减轻了简单基线中反卷积头网络的计算成本和参数，并引入了一种注意机制，该机制利用原始，层次和内部内部信息来增强准确性。此外，我们提出了一种称为热图加权损失的新型损耗函数，该功能为热图上的每个像素产生权重，从而使模型更加专注于关键点。实验证明我们的方法在性能，资源量和推理速度之间取得了平衡。具体而言，我们的方法可以在可可测试-DEV上获得65.3 AP得分，而推理速度分别为55 fps和18 fps，分别在移动GPU和CPU上。
Recent research on human pose estimation exploits complex structures to improve performance on benchmark datasets, ignoring the resource overhead and inference speed when the model is actually deployed. In this paper, we lighten the computation cost and parameters of the deconvolution head network in SimpleBaseline and introduce an attention mechanism that utilizes original, inter-level, and intra-level information to intensify the accuracy. Additionally, we propose a novel loss function called heatmap weighting loss, which generates weights for each pixel on the heatmap that makes the model more focused on keypoints. Experiments demonstrate our method achieves a balance between performance, resource volume, and inference speed. Specifically, our method can achieve 65.3 AP score on COCO test-dev, while the inference speed is 55 FPS and 18 FPS on the mobile GPU and CPU, respectively.
