Consistency-Aware Anchor Pyramid Network for Crowd Localization

作     者：Liu, Xinyan Li, Guorong Qi, Yuankai Han, Zhenjun Huang, Qingming Yang, Ming-Hsuan Sebe, Nicu 

作者机构：University of Chinese Academy of Science Beijing China Australian Institute for Machine Learning The University of Adelaide Australia Key Lab of Intell. Info. Process. Inst. of Comput. Tech. CAS Beijing China Peng Cheng Laboratory Shenzhen China University of California Merced United States University of Trento Italy 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2022年

核心收录：

摘      要：Crowd localization aims to predict the spatial position of humans in a crowd scenario. We observe that the performance of existing methods is challenged from two aspects: (i) ranking inconsistency between test and training phases;and (ii) fixed anchor resolution may underfit or overfit crowd densities of local regions. To address these problems, we design a supervision target reassignment strategy for training to reduce ranking inconsistency and propose an anchor pyramid scheme to adaptively determine the anchor density in each image region. Extensive experimental results on three widely adopted datasets (ShanghaiTech A & B, JHU-CROWD++, UCF-QNRF) demonstrate the favorable performance against several state-of-the-art methods. © 2022, CC BY.