Spatial Uncertainty-Aware Semi-Supervised Crowd Counting

TL;DR

This paper introduces a spatial uncertainty-aware semi-supervised crowd counting method that leverages high-confidence regions and a surrogate segmentation task to improve accuracy with less labeled data.

Contribution

It proposes a novel teacher-student framework using spatial uncertainty maps and a differential transformation layer for better semi-supervised crowd counting.

Findings

Outperforms state-of-the-art semi-supervised methods on four datasets.

Effectively utilizes unlabeled data through uncertainty-guided learning.

Addresses spatial inconsistency between tasks for more reliable predictions.

Abstract

Semi-supervised approaches for crowd counting attract attention, as the fully supervised paradigm is expensive and laborious due to its request for a large number of images of dense crowd scenarios and their annotations. This paper proposes a spatial uncertainty-aware semi-supervised approach via regularized surrogate task (binary segmentation) for crowd counting problems. Different from existing semi-supervised learning-based crowd counting methods, to exploit the unlabeled data, our proposed spatial uncertainty-aware 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.