Spatial Uncertainty-Aware Semi-Supervised Crowd Counting

The task of crowd counting in computer vision is to infer Semi-supervised approaches for crowd counting attract the number of people in images or videos. There is attention, as the fully supervised paradigm is expensive and an ever-increasing demand for automated crowd counting laborious due to its request for a large number of images techniques in various applications such as public safety, security of dense crowd scenarios and their annotations. This paper alerts, transport management proposes a spatial uncertainty-aware semi-supervised approach via regularized surrogate task (binary segmentation) for crowd counting problems. Different from existing semisupervised learning-based crowd counting methods, to exploit the unlabeled data, our proposed spatial uncertaintyaware teacher-student framework focuses on high confident regions' information while addressing the noisy supervision from the unlabeled data in an end-to-end manner. Specifically, we estimate the spatial uncertainty maps from the teacher model's surrogate task to guide the feature learning of the main task (density regression) and the surrogate task of the student model at the same time. Besides, we introduce a simple yet effective differential transformation layer to enforce the inherent spatial consistency regularization between the main task and the surrogate task in the student model, which helps the surrogate task to yield more reliable predictions and generates high-quality uncertainty maps. Thus, our model can also address the task-level perturbation problems that occur spatial inconsistency between the primary and surrogate tasks in the student model. Experimental results on four challenging crowd counting datasets demonstrate that our method achieves superior performance to the state-of-the-art semi-supervised methods. Code is available at: https://github.com/