Search Results for author:
Found 2 papers, 1 papers with code
LaplaceConfidence: a Graph-based Approach for Learning with Noisy Labels
We introduce LaplaceConfidence, a method that to obtain label confidence (i. e., clean probabilities) utilizing the Laplacian energy.
Semi-Supervised Learning with Multi-Head Co-Training
Co-training, extended from self-training, is one of the frameworks for semi-supervised learning.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
