Semi-supervised Crowd Counting via Density Agency

TL;DR

This paper introduces a semi-supervised crowd counting method that uses a novel density agency structure, contrastive learning, and noise reduction to improve accuracy on challenging datasets.

Contribution

It presents a new agency-guided semi-supervised approach with a density agency, contrastive loss, transformer-based regression head, and noise depression, advancing crowd counting techniques.

Findings

Achieves superior performance over state-of-the-art methods

Effective noise reduction improves counting accuracy

Demonstrates robustness across four challenging datasets

Abstract

In this paper, we propose a new agency-guided semi-supervised counting approach. First, we build a learnable auxiliary structure, namely the density agency to bring the recognized foreground regional features close to corresponding density sub-classes (agents) and push away background ones. Second, we propose a density-guided contrastive learning loss to consolidate the backbone feature extractor. Third, we build a regression head by using a transformer structure to refine the foreground features further. Finally, an efficient noise depression loss is provided to minimize the negative influence of annotation noises. Extensive experiments on four challenging crowd counting datasets demonstrate that our method achieves superior performance to the state-of-the-art semi-supervised counting methods by a large margin. Code is available.