论文标题
学习错误驱动的课程用于人群计数
Learning Error-Driven Curriculum for Crowd Counting
论文作者
论文摘要
密度回归已被广泛用于人群计数。但是，密度图中像素值的频率失衡仍然是提高性能的障碍。在本文中，我们提出了一种用于学习错误驱动课程的新型学习策略，该课程使用额外的网络来监督主网络的培训。提出了一个称为Tutornet的辅导网络，以重复指示主网络的关键错误。 Tutornet生成像素级的权重，以在培训过程中为主网络制定课程，因此主网络将为这些硬示例分配更高的权重，而不是简单的示例。此外，我们将密度图扩大以扩大审查间距离的因素，这是众所周知的，这是可以改善性能的。在两个具有挑战性的基准数据集上进行了广泛的实验表明，我们的方法已经达到了最先进的性能。
Density regression has been widely employed in crowd counting. However, the frequency imbalance of pixel values in the density map is still an obstacle to improve the performance. In this paper, we propose a novel learning strategy for learning error-driven curriculum, which uses an additional network to supervise the training of the main network. A tutoring network called TutorNet is proposed to repetitively indicate the critical errors of the main network. TutorNet generates pixel-level weights to formulate the curriculum for the main network during training, so that the main network will assign a higher weight to those hard examples than easy examples. Furthermore, we scale the density map by a factor to enlarge the distance among inter-examples, which is well known to improve the performance. Extensive experiments on two challenging benchmark datasets show that our method has achieved state-of-the-art performance.
