论文标题
人群计数的分布匹配
Distribution Matching for Crowd Counting
论文作者
论文摘要
在人群计数中，每个培训图像都包含多个人，每个人都会被一个点注释。现有的人群计数方法需要使用高斯来平滑每个带注释的点，或者估计每个像素给定点的可能性。在本文中，我们表明，对注释强加于注释会损害泛化的表现。相反，我们建议将分布匹配用于人群计数（DM计数）。在DM计数中，我们使用最佳传输（OT）来测量标准化预测密度图与标准化地面真相密度图之间的相似性。为了稳定OT计算，我们在模型中包括总变化损失。我们表明，DM计数的概括误差比高斯平滑方法更紧密。在平均绝对误差方面，DM计数的表现优于先前的最先进方法，在两个大规模计数数据集（UCF-QNRF和NWPU）上的差距很大，并在上海和UCF-CC50数据集中实现了最新的结果。 DM计数将最新发布结果的错误降低了约16％。代码可在https://github.com/cvlab-stonybrook/dm-count上找到。
In crowd counting, each training image contains multiple people, where each person is annotated by a dot. Existing crowd counting methods need to use a Gaussian to smooth each annotated dot or to estimate the likelihood of every pixel given the annotated point. In this paper, we show that imposing Gaussians to annotations hurts generalization performance. Instead, we propose to use Distribution Matching for crowd COUNTing (DM-Count). In DM-Count, we use Optimal Transport (OT) to measure the similarity between the normalized predicted density map and the normalized ground truth density map. To stabilize OT computation, we include a Total Variation loss in our model. We show that the generalization error bound of DM-Count is tighter than that of the Gaussian smoothed methods. In terms of Mean Absolute Error, DM-Count outperforms the previous state-of-the-art methods by a large margin on two large-scale counting datasets, UCF-QNRF and NWPU, and achieves the state-of-the-art results on the ShanghaiTech and UCF-CC50 datasets. DM-Count reduced the error of the state-of-the-art published result by approximately 16%. Code is available at https://github.com/cvlab-stonybrook/DM-Count.
