31 citations · 62 across the 6 of their papers we have counts for
4 papers · 1 filter
Score-based Generative Modeling Through Backward Stochastic Differential Equations: Inversion and Generation
Zihao Wang
The proposed BSDE-based diffusion model represents a novel approach to diffusion modeling, which extends the application of stochastic differential equations (SDEs) in machine lear…
Tackling Instance-Dependent Label Noise with Dynamic Distribution Calibration
Manyi Zhang, Yuxin Ren, Zihao Wang +1
Instance-dependent label noise is realistic but rather challenging, where the label-corruption process depends on instances directly. It causes a severe distribution shift between…
End-To-End Graph-based Deep Semi-Supervised Learning
Zihao Wang, Enmei Tu, Zhou Meng
The quality of a graph is determined jointly by three key factors of the graph: nodes, edges and similarity measure (or edge weights), and is very crucial to the success of graph-b…
Semi-Supervised Deep Learning Using Improved Unsupervised Discriminant Projection
Xiao Han, Zihao Wang, Enmei Tu +2
Deep learning demands a huge amount of well-labeled data to train the network parameters. How to use the least amount of labeled data to obtain the desired classification accuracy…