计算机科学
判别式
利用
人工智能
注意力网络
机器学习
补偿(心理学)
计算机安全
心理学
精神分析
作者
Xinxing Su,Yuhong Yuan,Xiangbo Su,Zhikang Zou,Shifeng Wen,Pan Zhou
标识
DOI:10.1109/icpr48806.2021.9412883
摘要
An essential yet challenging issue in crowd counting is the diverse background variations under complicated real-life environments, which makes attention based methods favorable in recent years. However, most existing methods only rely on first-order attention schemes (e.g. 2D position-wise attention), while ignoring the higher-order information within the congested scenes completely. In this paper, we propose a hybrid attention-aware network (HANet) with a high-order attention module (HAM) and an adaptive compensation loss (ACLoss) to tackle this problem. On the one hand, the HAM applies 3D attention to capture the subtle discriminative features around each people in the crowd. On the other hand, with the distributed supervision, the ACLoss exploits the prior knowledge from higher-level stages to guide the density map prediction at a lower level. The proposed HANet is then established with HAM and ACLoss working as different roles and promoting each other. Extensive experimental results show the superiority of our HANet against the state-of-the-arts on three challenging benchmarks.
科研通智能强力驱动
Strongly Powered by AbleSci AI