Significant progress on the crowd counting problem has been achieved by
integrating larger context into convolutional neural networks (CNNs). This
indicates that global scene context is essential, despite the see
该研究提出了一种新的半监督方法,基于平均教师框架,以减轻训练可靠的人群计数模型所需的大量标注负担,从而增加数据量,提高模型的实用性和准确性。经验证明,在标签数据稀缺的情况下,仅通过未标记的数据来提高局部区域预测的准确性是不充分的,因此需要采用更细粒度的方法培养模型的内在 “突显” 能力,以 accurately estimate the count in regions by leveraging its understanding of the crowd scenes,并结合局部细节预测高密度区域,该方法在人群计数领域取得了最先进的表现。