Semi-supervised Crowd Counting via Density Agency

by   Hui Lin, et al.

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.


page 1

page 3

page 7


Semi-Supervised Crowd Counting via Self-Training on Surrogate Tasks

Most existing crowd counting systems rely on the availability of the obj...

Counting with Adaptive Auxiliary Learning

This paper proposes an adaptive auxiliary task learning based approach f...

CCTrans: Simplifying and Improving Crowd Counting with Transformer

Most recent methods used for crowd counting are based on the convolution...

Spatial Uncertainty-Aware Semi-Supervised Crowd Counting

Semi-supervised approaches for crowd counting attract attention, as the ...

Focus for Free in Density-Based Counting

This work considers supervised learning to count from images and their c...

Cross-head Supervision for Crowd Counting with Noisy Annotations

Noisy annotations such as missing annotations and location shifts often ...

HDNet: A Hierarchically Decoupled Network for Crowd Counting

Recently, density map regression-based methods have dominated in crowd c...

Please sign up or login with your details

Forgot password? Click here to reset