1k citations · 2.3k across the 46 of their papers we have counts for
7 papers · 1 filter
Knowledge Concentration: Learning 100K Object Classifiers in a Single CNN
Jiyang Gao, Zijian, Guo +2
Fine-grained image labels are desirable for many computer vision applications, such as visual search or mobile AI assistant. These applications rely on image classification models…
Understanding Hidden Memories of Recurrent Neural Networks
Yao Ming, Shaozu Cao, Ruixiang Zhang +4
Recurrent neural networks (RNNs) have been successfully applied to various natural language processing (NLP) tasks and achieved better results than conventional methods. However, t…
High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference
Xiaoguang Han, Zhen Li, Haibin Huang +2
We propose a data-driven method for recovering miss-ing parts of 3D shapes. Our method is based on a new deep learning architecture consisting of two sub-networks: a global structu…
A Flow Model of Neural Networks
Zhen Li, Zuoqiang Shi
Based on a natural connection between ResNet and transport equation or its characteristic equation, we propose a continuous flow model for both ResNet and plain net. Through this c…
Deep Residual Learning and PDEs on Manifold
Zhen Li, Zuoqiang Shi
In this paper, we formulate the deep residual network (ResNet) as a control problem of transport equation. In ResNet, the transport equation is solved along the characteristics. Ba…
Learning Gaussian Graphical Models Using Discriminated Hub Graphical Lasso
Zhen Li, Jingtian Bai, Weilian Zhou
We develop a new method called Discriminated Hub Graphical Lasso (DHGL) based on Hub Graphical Lasso (HGL) by providing prior information of hubs. We apply this new method in two s…
Predicting membrane protein contacts from non-membrane proteins by deep transfer learning
Zhen Li, Sheng Wang, Yizhou Yu +1
Computational prediction of membrane protein (MP) structures is very challenging partially due to lack of sufficient solved structures for homology modeling. Recently direct evolut…