Biography

Le Zhang is a scientist at Institute for Infocomm Research, Agency for Science, Technology and Re- search (A*STAR), Singapore. He received the B.Eng degree from University of Electronic Science and Technology of China (UESTC) in 2011, the M.SC from Nanyang Technological University (NTU) in 2012, the Ph.D degree from Nanyang Technological University (NTU) in 2016. During 2016-2018, he was a postdoc researcher at the advanced digital sciences center, a research affiliate with the Coordi- nate Science Laboratory of University of Illinois at Urbana-Champaign. His current research interests include deep learning and computer vision. He has published more than 30 papers in peer reviewed journals/conferences. His publications have been well cited.Their team's technology on multimodal emotion recognition was shortlisted as a finalist for the IET Innovation Awards 2018 among 350 entries from all over the world.

Abstract

Deep convolutional networks (ConvNets) have achieved unprecedented performances on many com- puter vision tasks. However, their adaptations to crowd counting on single images are still in their infan- cy and suffer from severe over-fitting. Here we propose a new learning strategy to produce generaliz- able 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-ofthe-art methods. Our implementation will be released at https://github.com/shizenglin/Deep-NCL.