Noisy annotations such as missing annotations and location shifts often exist in crowd counting datasets due to multi-scale head sizes, high occlusion, etc. These noisy annotations severely affect the model training, especially for density map-based methods. To alleviate the negative impact of noisy annotations, we propose a novel crowd counting model with one convolution head and one transformer head, in which these two heads can supervise each other in noisy areas, called Cross-Head Supervision. The resultant model, CHS-Net, can synergize different types of inductive biases for better counting. In addition, we develop a progressive cross-head supervision learning strategy to stabilize the training process and provide more reliable supervision. Extensive experimental results on ShanghaiTech and QNRF datasets demonstrate superior performance over state-of-the-art methods. Code is available at https://github.com/RaccoonDML/CHSNet.

翻译：由于多尺度头部尺寸、高度遮挡等因素，人群计数数据集中常存在缺失标注、位置偏移等噪声标注问题。这些噪声标注严重干扰模型训练，尤其对基于密度图的方法影响显著。为缓解噪声标注的负面影响，我们提出一种新型人群计数模型，该模型包含一个卷积头和一个Transformer头，两者可在噪声区域相互监督，称为跨头监督（Cross-Head Supervision）。由此生成的模型CHS-Net能够协同不同归纳偏置实现更优计数。此外，我们设计了一种渐进式跨头监督学习策略，以稳定训练过程并提供更可靠的监督信息。在ShanghaiTech和QNRF数据集上的大量实验结果表明，该方法性能优于现有最优模型。代码已开源：https://github.com/RaccoonDML/CHSNet。