Attention Scaling for Crowd Counting

By Xiaoheng Jiang, Li Zhang, Mingliang Xu, Tianzhu Zhang, Pei Lv, Bing Zhou, Xin Yang, Yanwei Pang. Computer Vision and Pattern Recognition, 2020

307 citations recorded by the source corpus.

Convolutional Neural Network (CNN) based methods generally take crowd counting as a regression task by outputting crowd densities. They learn the mapping between image contents and crowd density distributions. Though having achieved promising results, these data-driven counting networks are prone to overestimate or underestimate people counts of regions with different density patterns, which degrades the whole count accuracy. To overcome this problem, we propose an approach to alleviate the counting performance differences in different regions. Specifically, our approach consists of two networks named Density Attention Network (DANet) and Attention Scaling Network (ASNet). DANet provides ASNet with attention masks related to regions of different density levels. ASNet first generates density maps and scaling factors and then multiplies them by attention masks to output separate attention-based density maps. These density maps are summed to give the final density map. The attention scaling factors help attenuate the estimation errors in different regions. Furthermore, we present a novel Adaptive Pyramid Loss (APLoss) to hierarchically calculate the estimation losses of sub-regions, which alleviates the training bias. Extensive experiments on four challenging datasets (ShanghaiTech Part A, UCF_CC_50, UCF-QNRF, and WorldExpo'10) demonstrate the superiority of the proposed approach.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Safety, Risk, Reliability and Quality

View Paper: https://www.semanticscholar.org/paper/de0031a476f18208eb41de5fce2801e3c2368dce

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Ying Tai
2. Feiyue Huang
3. Chengjie Wang
4. Changan Wang
5. Yang Wu
6. Yabiao Wang
7. Jilin Li
8. Zhengkai Jiang

In Computer Vision and Pattern Recognition

1. Ying Tai
2. Qingyu Song
3. Feiyue Huang
4. Chengjie Wang
5. Changan Wang
6. Yang Wu
7. Yabiao Wang
8. Jilin Li

Citations in the corpus

• Rethinking Counting and Localization in Crowds: A Purely Point-Based Framework (2021, background): “They either conduct a pixel-wise density map regression [16, 28, 11, 1, 25, 8], or resort to classify the count value of local patch into several bins [39, 21, 22].”