G
Gao Huang
Researcher at Tsinghua University
Publications - 164
Citations - 43663
Gao Huang is an academic researcher from Tsinghua University. The author has contributed to research in topics: Computer science & Feature (computer vision). The author has an hindex of 37, co-authored 124 publications receiving 26697 citations. Previous affiliations of Gao Huang include Cornell University & University of Science and Technology of China.
Papers
More filters
Journal ArticleDOI
Dynamic Minimax Probability Machine-Based Approach for Fault Diagnosis Using Pairwise Discriminate Analysis
TL;DR: A dynamic minimax probability machine approach based on the framework of probabilistic representations is proposed for diagnosing process faults, without imposing any assumptions on data distributions, and is demonstrated on the Tennessee Eastman process.
Posted ContentDOI
Assisting Scalable Diagnosis Automatically via CT Images in the Combat against COVID-19
Bohan Liu,Pan Liu,Lutao Dai,Yan-Lin Yang,Peng Xie,Yiqing Tan,Jicheng Du,Wei Shan,Chenghui Zhao,Qin Zhong,Xixiang Lin,Xizhou Guan,Ning Xing,Yuhui Sun,Wenjun Wang,Zhibing Zhang,Xia Fu,Yanqing Fan,Meifang Li,Na Zhang,Lin Li,Yaou Liu,Lin Xu,J Du,Zhenhua Zhao,Xuelong Hu,Weipeng Fan,Rongpin Wang,Chongchong Wu,Yongkang Nie,Liuquan Cheng,Lin Ma,Zongren Li,Jia Qian,Liu Minchao,Guo Huayuan,Gao Huang,Haipeng Shen,Weimin An,Hao Li,Jianxin Zhou,Kunlun He +41 more
TL;DR: In this article, a modified DenseNet-264 model, COVIDNet, was used to classify CT images to either class, achieving an accuracy of 94.3% and an area under the curve (AUC) of 0.98.
Journal ArticleDOI
Gated Path Selection Network for Semantic Segmentation
TL;DR: Gated Path Selection Network (GPSNet) as discussed by the authors proposes a two-dimensional SuperNet which densely incorporates features from growing receptive fields and a Comparative Feature Aggregation (CFA) module is introduced to dynamically aggregate discriminative semantic context.
Journal Article
Meta-Semi: A Meta-learning Approach for Semi-supervised Learning
TL;DR: A novel meta-learning based SSL algorithm (Meta-Semi) that requires tuning only one additional hyper-parameter, compared with a standard supervised deep learning algorithm, to achieve competitive performance under various conditions of SSL.
Proceedings Article
Regularized Anderson Acceleration for Off-Policy Deep Reinforcement Learning
TL;DR: This work proposes a general acceleration method for model-free, off-policy deep RL algorithms by drawing the idea underlying regularized Anderson acceleration (RAA), which is an effective approach to accelerating the solving of fixed point problems with perturbations.