Self-Augmentation Based on Noise-Robust Probabilistic Model for Noisy Labels
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Access"
DOI: 10.1109/access.2022.3219810
Abstract: Learning deep neural networks from noisy labels is challenging, because high-capacity networks attempt to describe data even with noisy class labels. In this study, we propose a self-augmentation method without additional parameters, which handles noisy… read more here.
Keywords: noisy labels; small loss; probabilistic model; model ... See more keywords
JoSDW: Combating Noisy Labels by Dynamic Weight
Sign Up to like & getrecommendations! Published in 2022 at "Future Internet"
DOI: 10.3390/fi14020050
Abstract: The real world is full of noisy labels that lead neural networks to perform poorly because deep neural networks (DNNs) are prone to overfitting label noise. Noise label training is a challenging problem relating to… read more here.
Keywords: noisy labels; sample; small loss; dynamic weight ... See more keywords