English

Cross-head Supervision for Crowd Counting with Noisy Annotations

Computer Vision and Pattern Recognition 2023-10-03 v1

Abstract

Noisy annotations such as missing annotations and location shifts often exist in crowd counting datasets due to multi-scale head sizes, high occlusion, etc. These noisy annotations severely affect the model training, especially for density map-based methods. To alleviate the negative impact of noisy annotations, we propose a novel crowd counting model with one convolution head and one transformer head, in which these two heads can supervise each other in noisy areas, called Cross-Head Supervision. The resultant model, CHS-Net, can synergize different types of inductive biases for better counting. In addition, we develop a progressive cross-head supervision learning strategy to stabilize the training process and provide more reliable supervision. Extensive experimental results on ShanghaiTech and QNRF datasets demonstrate superior performance over state-of-the-art methods. Code is available at https://github.com/RaccoonDML/CHSNet.

Keywords

Cite

@article{arxiv.2303.09245,
  title  = {Cross-head Supervision for Crowd Counting with Noisy Annotations},
  author = {Mingliang Dai and Zhizhong Huang and Jiaqi Gao and Hongming Shan and Junping Zhang},
  journal= {arXiv preprint arXiv:2303.09245},
  year   = {2023}
}

Comments

accepted by ICASSP 2023

R2 v1 2026-06-28T09:20:03.025Z