Crowd Counting With Deep Negative Correlation Learning

Zenglin Shi, Le Zhang, Yun Liu, Xiaofeng Cao, Yangdong Ye, Ming-Ming Cheng, Guoyan Zheng; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 5382-5390


Deep convolutional networks (ConvNets) have achieved unprecedented performances on many computer vision tasks. However, their adaptations to crowd counting on single images are still in their infancy and suffer from severe over-fitting. Here we propose a new learning strategy to produce generalizable features by way of deep negative correlation learning (NCL). More specifically, we deeply learn a pool of decorrelated regressors with sound generalization capabilities through managing their intrinsic diversities. Our proposed method, named decorrelated ConvNet (D-ConvNet), is end-to-end-trainable and independent of the backbone fully-convolutional network architectures. Extensive experiments on very deep VGGNet as well as our customized network structure indicate the superiority of D-ConvNet when compared with several state-of-the-art methods. Our implementation will be released at

Related Material

author = {Shi, Zenglin and Zhang, Le and Liu, Yun and Cao, Xiaofeng and Ye, Yangdong and Cheng, Ming-Ming and Zheng, Guoyan},
title = {Crowd Counting With Deep Negative Correlation Learning},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}