Calibrating Uncertainty for Semi-Supervised Crowd Counting

TL;DR

This paper introduces a novel uncertainty calibration method for semi-supervised crowd counting, improving pseudo-label quality and achieving state-of-the-art results by better estimating uncertainty through a matching-based surrogate function.

Contribution

It proposes a new uncertainty calibration technique using a matching-based surrogate function for crowd counting, enhancing pseudo-label reliability in semi-supervised learning.

Findings

Achieves state-of-the-art semi-supervised crowd counting performance.

Generates high-quality pseudo-labels with calibrated uncertainty.

Improves model reliability through a novel surrogate function.

Abstract

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.