Semi-Supervised Multi-View Crowd Counting by Ranking Multi-View Fusion Models
Authors:
- Qi ZhangQZQi Zhang
- Yunfei GongYGYunfei Gong
- Zhidan XieZXZhidan Xie
- Zhizi WangZWZhizi Wang
- Antoni B. ChanACAntoni B. Chan
- Hui HuangHHHui Huang
Preprint
Abstract
Multi-view crowd counting has been proposed to deal with the severe occlusion issue of crowd counting in large and wide scenes. However, due to the difficulty of collecting and annotating multi-view images, the datasets for multi-view counting have a limited number of multi-view frames and scenes. To solve the problem of limited data, one approach is to collect synthetic data to bypass the annotating step, while another is to propose semi- or weakly-supervised or unsupervised methods that demand less multi-view data. In this paper, we propose two semi-supervised multi-view crowd counting frameworks by ranking the multi-view fusion models of different numbers of input views, in terms of the model predictions or the model uncertainties. Specifically, for the first method (vanilla model), we rank the multi-view fusion models' prediction results of different numbers of camera-view inputs, namely, the model's predictions with fewer camera views shall not be larger than the predictions with more camera views. For the second method, we rank the estimated model uncertainties of the multi-view fusion models with a variable number of view inputs, guided by the multi-view fusion models' prediction errors, namely, the model uncertainties with more camera views shall not be larger than those with fewer camera views. These constraints are introduced into the model training in a semi-supervised fashion for multi-view counting with limited labeled data. The experiments demonstrate the advantages of the proposed multi-view model ranking methods compared with other semi-supervised counting methods.Keywords
All Related Versions
This publication has 18 references indexed in Scilit:
- CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise Classification2025
- Rethinking Counting and Localization in Crowds: A Purely Point-Based Framework2021
- Learning to Count in the Crowd from Limited Labeled Data2020
- Semi-supervised Crowd Counting via Self-training on Surrogate Tasks2020
- Active Crowd Counting with Limited Supervision2020
- Weakly-Supervised Crowd Counting Learns from Sorting Rather Than Locations2020
- Learning From Synthetic Data for Crowd Counting in the Wild2019
- Context-Aware Crowd Counting2019
- PETS2009: Dataset and challenge2009
- Robust Real-Time Face DetectionInternational Journal of Computer Vision, 2004