Calibrating Uncertainty for Semi-Supervised Crowd Counting
This addresses the challenge of accurate crowd counting with limited labeled data, which is important for applications like public safety and urban planning, but the approach appears incremental as it builds on existing pseudo-labeling methods.
The paper tackles the problem of semi-supervised crowd counting by proposing a method to calibrate model uncertainty for selecting reliable pseudo-labels, achieving state-of-the-art performance.
Semi-supervised crowd counting is an important yet challenging task. A popular approach is to iteratively generate pseudo-labels for unlabeled data and add them to the training set. The key is to use uncertainty to select reliable pseudo-labels. In this paper, we propose a novel method to calibrate model uncertainty for crowd counting. Our method takes a supervised uncertainty estimation strategy to train the model through a surrogate function. This ensures the uncertainty is well controlled throughout the training. We propose a matching-based patch-wise surrogate function to better approximate uncertainty for crowd counting tasks. The proposed method pays a sufficient amount of attention to details, while maintaining a proper granularity. Altogether our method is able to generate reliable uncertainty estimation, high quality pseudolabels, and achieve state-of-the-art performance in semisupervised crowd counting.