Zenglin Shi, Le Zhang*, Yun Liu, Xiaofeng Cao, Yangdong Ye, Ming-Ming Cheng and Guoyan Zheng
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 5382-5390)
Publication year: 2018

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 se- vere 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 gener- alization capabilities through managing their intrinsic di- versities. Our proposed method, named decorrelated Con- vNet (D-ConvNet), is end-to-end-trainable and indepen- dent of the backbone fully-convolutional network architec- tures. 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. Project page is available at https://github.com/shizenglin/Deep-NCL

发表评论

邮箱地址不会被公开。 必填项已用*标注