论文标题
半监督人群通过密度代理进行计数
Semi-supervised Crowd Counting via Density Agency
论文作者
论文摘要
在本文中，我们提出了一种新的机构指导的半监督计数方法。首先，我们建立了一个可学习的辅助结构，即密度机构将公认的前景区域特征带到相应的密度子类（代理）和推开背景的区域。其次，我们提出了一个密度引导的对比度学习损失，以巩固骨干特征提取器。第三，我们通过使用变压器结构进一步完善前景特征来建立回归头。最后，提供有效的噪声降低损失，以最大程度地减少注释噪声的负面影响。对四个挑战的人群计数数据集进行了广泛的实验表明，我们的方法在很大的边距上实现了与最先进的半监督计数方法相比最先进的性能。代码可用。
In this paper, we propose a new agency-guided semi-supervised counting approach. First, we build a learnable auxiliary structure, namely the density agency to bring the recognized foreground regional features close to corresponding density sub-classes (agents) and push away background ones. Second, we propose a density-guided contrastive learning loss to consolidate the backbone feature extractor. Third, we build a regression head by using a transformer structure to refine the foreground features further. Finally, an efficient noise depression loss is provided to minimize the negative influence of annotation noises. Extensive experiments on four challenging crowd counting datasets demonstrate that our method achieves superior performance to the state-of-the-art semi-supervised counting methods by a large margin. Code is available.
