Search Results for author:
Found 2 papers, 0 papers with code
Potential Energy based Mixture Model for Noisy Label Learning
Training deep neural networks (DNNs) from noisy labels is an important and challenging task.
Uncertainty-aware self-training with expectation maximization basis transformation
Specifically, we propose to use Expectation-Maximization (EM) to smooth the labels and comprehensively estimate the uncertainty information.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
