For tackling the task of 2D human pose estimation, the great majority of the recent methods regard this task as a heatmap estimation problem, and optimize the heatmap prediction using the Gaussian-smoothed heatmap as the optimization objective and using the pixel-wise loss (e.g. MSE) as the loss function. In this paper, we show that optimizing the heatmap prediction in such a way, the model performance of body joint localization, which is the intrinsic objective of this task, may not be consistently improved during the optimization process of the heatmap prediction. To address this problem, from a novel perspective, we propose to formulate the optimization of the heatmap prediction as a distribution matching problem between the predicted heatmap and the dot annotation of the body joint directly. By doing so, our proposed method does not need to construct the Gaussian-smoothed heatmap and can achieve a more consistent model performance improvement during the optimization of the heatmap prediction. We show the effectiveness of our proposed method through extensive experiments on the COCO dataset and the MPII dataset.
翻译:为了处理2D人造估计的任务,大多数最近的方法都认为这项任务是一个热图估计问题,并且优化热图预测,将高森悬浮热图作为优化目标,并将像素-方法损失(如MSE)作为损失函数。在本文件中,我们表明,以这种方式优化热图预测,作为这项任务内在目标的体合局部化模型性能在热图预测优化过程中可能无法不断改进。为了解决这一问题,我们从新角度出发,建议将热图预测优化成一个分布匹配问题,直接将预测的热图与身体的圆点注结合起来。这样,我们建议的方法就不需要以这种方式构建高斯悬浮热图,可以在优化热图预测过程中实现更加一致的模型性能改进。我们通过对CO数据集和MPII数据集的广泛实验来展示我们所提议的方法的有效性。