To alleviate the heavy annotation burden for training a reliable crowd counting model and thus make the model more practicable and accurate by being able to benefit from more data, this paper presents a new semi-supervised method based on the mean teacher framework. When there is a scarcity of labeled data available, the model is prone to overfit local patches. Within such contexts, the conventional approach of solely improving the accuracy of local patch predictions through unlabeled data proves inadequate. Consequently, we propose a more nuanced approach: fostering the model's intrinsic 'subitizing' capability. This ability allows the model to accurately estimate the count in regions by leveraging its understanding of the crowd scenes, mirroring the human cognitive process. To achieve this goal, we apply masking on unlabeled data, guiding the model to make predictions for these masked patches based on the holistic cues. Furthermore, to help with feature learning, herein we incorporate a fine-grained density classification task. Our method is general and applicable to most existing crowd counting methods as it doesn't have strict structural or loss constraints. In addition, we observe that the model trained with our framework exhibits a 'subitizing'-like behavior. It accurately predicts low-density regions with only a 'glance', while incorporating local details to predict high-density regions. Our method achieves the state-of-the-art performance, surpassing previous approaches by a large margin on challenging benchmarks such as ShanghaiTech A and UCF-QNRF. The code is available at: https://github.com/cha15yq/MRC-Crowd.

翻译：为了减轻训练可靠人群计数模型的重标注负担，从而通过从更多数据中获益使模型更具实用性和准确性，本文提出了一种基于均值教师框架的新型半监督方法。在标注数据稀缺的情况下，模型容易过拟合局部区域。在此背景下，仅通过未标注数据提高局部区域预测准确性的传统方法被证明是不充分的。因此，我们提出了一种更细致的方法：培养模型内在的“瞬数”能力。这种能力使模型能够通过利用对人群场景的理解准确估计区域中的计数，类似于人类的认知过程。为实现这一目标，我们对未标注数据应用掩码，引导模型基于全局线索对这些掩码区域进行预测。此外，为辅助特征学习，我们引入了一项细粒度密度分类任务。由于该方法没有严格的结构或损失约束，因此具有通用性，可适用于大多数现有的人群计数方法。另外，我们观察到，使用我们的框架训练的模型表现出类似“瞬数”的行为：它能够仅通过“一瞥”准确预测低密度区域，同时结合局部细节预测高密度区域。我们的方法实现了最先进的性能，在ShanghaiTech A和UCF-QNRF等具有挑战性的基准测试上大幅超越了先前方法。代码可在https://github.com/cha15yq/MRC-Crowd获取。