no code implementations • 12 Apr 2019 • Fang Su, Hai-Yang Shang, Jing-Yan Wang
Meanwhile, we also propose to regularize another fully connected layer by sparsity penalty, so that the useful features learned by the lower layers can be selected.
no code implementations • 17 May 2018 • Guohui Zhang, Gaoyuan Liang, Fang Su, Fanxin Qu, Jing-Yan Wang
We proposed to embed the attributes of dif-ferent domains by a shared convolutional neural network (CNN), learn a domain-independent CNN model to represent the information shared by dif-ferent domains by matching across domains, and a domain-specific CNN model to represent the information of each domain.
no code implementations • 26 Mar 2018 • Fang Su, Jing-Yan Wang
In the transfer learning problem, we want to leverage the data of the auxiliary and the target domains to build an effective model for the classification problem in the target domain.