2 papers
cs.LG2024
Potential Energy based Mixture Model for Noisy Label Learning
Zijia Wang, Wenbin Yang, Zhisong Liu +1
Training deep neural networks (DNNs) from noisy labels is an important and challenging task. However, most existing approaches focus on the corrupted labels and ignore the importan…
cs.CV2024
Uncertainty-aware self-training with expectation maximization basis transformation
Zijia Wang, Wenbin Yang, Zhisong Liu +1
Self-training is a powerful approach to deep learning. The key process is to find a pseudo-label for modeling. However, previous self-training algorithms suffer from the over-confi…