Can I read Tackling Noisy Labels with Network Parameter Additive Decomposition on EtoBox?

Tackling Noisy Labels with Network Parameter Additive Decomposition by Wang, Jingyi; Xia, Xiaobo; Lan, Long; Wu, Xinghao; Yu, Jun; Yang, Wenjing; Han, Bo; Liu, Tongliang is a scholarly article available to read on EtoBox.

What is Tackling Noisy Labels with Network Parameter Additive Decomposition about?

Given data with noisy labels, over-parameterized deep networks suffer overfitting mislabeled data, resulting in poor generalization. The memorization effect of deep networks shows that although the networks have the ability to memorize all noisy data, they would first memorize clean training data, and then gradually memorize mislabeled training data. A simple and effective method that exploits the memorization effect to combat noisy labels is early stopping. However, early stopping cannot distinguish the memorization of clean data and mislabeled data, resulting in the network still inevitably overfitting mislabeled data in the early training stage.In this paper, to decouple the memorization of clean data and mislabeled data, and further reduce the side effect of mislabeled data, we perform additive decomposition on network parameters. Namely, all parameters are additively decomposed into two groups, i.e., parameters $\mathbf{w}$ are decomposed as $\mathbf{w}=\bm{\sigma}+\bm{\gamma}$. Afterward, the parameters $\bm{\sigma}$ are considered to memorize clean data, while the parameters $\bm{\gamma}$ are considered to memorize mislabeled data. Benefiting from the memorization effect, th

Author

Wang, Jingyi; Xia, Xiaobo; Lan, Long; Wu, Xinghao; Yu, Jun; Yang, Wenjing; Han, Bo; Liu, Tongliang

Published

2024

Language

EN