Multi-Step Quantization Of A Multi-Scale Network For Crowd Counting

Author(s):  
Kyujin Shim ◽  
Junyoung Byun ◽  
Changick Kim
2021 ◽  
pp. 403-417
Author(s):  
Jinfang Zheng ◽  
Panpan Zhao ◽  
Jinyang Xie ◽  
Chen Lyu ◽  
Lei Lyu

2020 ◽  
Vol 1650 ◽  
pp. 032070
Author(s):  
Pengze Wang ◽  
Wei Wu ◽  
Yang Su ◽  
Xin Li ◽  
Yongsheng Duan

Author(s):  
Ying Shi ◽  
Jun Sang ◽  
Mohammad S. Alam ◽  
Xinyue Liu ◽  
Shaoli Tian

Author(s):  
Anran Zhang ◽  
Xiaolong Jiang ◽  
Baochang Zhang ◽  
Xianbin Cao
Keyword(s):  

2020 ◽  
Vol 34 (07) ◽  
pp. 11693-11700 ◽  
Author(s):  
Ao Luo ◽  
Fan Yang ◽  
Xin Li ◽  
Dong Nie ◽  
Zhicheng Jiao ◽  
...  

Crowd counting is an important yet challenging task due to the large scale and density variation. Recent investigations have shown that distilling rich relations among multi-scale features and exploiting useful information from the auxiliary task, i.e., localization, are vital for this task. Nevertheless, how to comprehensively leverage these relations within a unified network architecture is still a challenging problem. In this paper, we present a novel network structure called Hybrid Graph Neural Network (HyGnn) which targets to relieve the problem by interweaving the multi-scale features for crowd density as well as its auxiliary task (localization) together and performing joint reasoning over a graph. Specifically, HyGnn integrates a hybrid graph to jointly represent the task-specific feature maps of different scales as nodes, and two types of relations as edges: (i) multi-scale relations capturing the feature dependencies across scales and (ii) mutual beneficial relations building bridges for the cooperation between counting and localization. Thus, through message passing, HyGnn can capture and distill richer relations between nodes to obtain more powerful representations, providing robust and accurate results. Our HyGnn performs significantly well on four challenging datasets: ShanghaiTech Part A, ShanghaiTech Part B, UCF_CC_50 and UCF_QNRF, outperforming the state-of-the-art algorithms by a large margin.


Sign in / Sign up

Export Citation Format

Share Document