Reducing Spatial Labeling Redundancy for Active Semi-Supervised Crowd Counting

• Main Authors: LIU, Yongtuo, REN, Sucheng, CHAI, Liangyu, WU, Hanjie, XU, Dan, QIN, Jing, HE, Shengfeng
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: Crowd counting; Features extraction; Head; Labelings; Semi-supervised; Semi-supervised learning; Spatial labeling redundancy; Technological innovation; Termination of employment; Databases and Information Systems; Technology and Innovation
• Online Access: https://ink.library.smu.edu.sg/sis_research/8435; https://ink.library.smu.edu.sg/context/sis_research/article/9438/viewcontent/Reducing_Spatial_Labeling_Redundancy_for_Active_Semi_Supervised_Crowd_Counting__1_.pdf
• Institution: Singapore Management University

Labeling is onerous for crowd counting as it should annotate each individual in crowd images. Recently, several methods have been proposed for semi-supervised crowd counting to reduce the labeling efforts. Given a limited labeling budget, they typically select a few crowd images and densely label all individuals in each of them. Despite the promising results, we argue the None-or-All labeling strategy is suboptimal as the densely labeled individuals in each crowd image usually appear similar while the massive unlabeled crowd images may contain entirely diverse individuals. To this end, we propose to break the labeling chain of previous methods and make the first attempt to reduce spatial labeling redundancy for semi-supervised crowd counting. First, instead of annotating all the regions in each crowd image, we propose to annotate the representative ones only. We analyze the region representativeness from both vertical and horizontal directions of initially estimated density maps, and formulate them as cluster centers of Gaussian Mixture Models. Additionally, to leverage the rich unlabeled regions, we exploit the similarities among individuals in each crowd image to directly supervise the unlabeled regions via feature propagation instead of the error-prone label propagation employed in the previous methods. In this way, we can transfer the original spatial labeling redundancy caused by individual similarities to effective supervision signals on the unlabeled regions. Extensive experiments on the widely-used benchmarks demonstrate that our method can outperform previous best approaches by a large margin.