Self-paced Resistance Learning against Overfitting on Noisy Labels
This addresses the issue of noisy labels corrupting CNNs for practitioners in data-scarce domains, though it is an incremental improvement on existing curriculum learning approaches.
The paper tackles the problem of noisy labels degrading convolutional neural network performance by proposing a self-paced resistance framework that learns a curriculum from confident samples and uses a resistance loss to prevent overfitting, achieving significantly superior results over state-of-the-art methods without clean validation data.
Noisy labels composed of correct and corrupted ones are pervasive in practice. They might significantly deteriorate the performance of convolutional neural networks (CNNs), because CNNs are easily overfitted on corrupted labels. To address this issue, inspired by an observation, deep neural networks might first memorize the probably correct-label data and then corrupt-label samples, we propose a novel yet simple self-paced resistance framework to resist corrupted labels, without using any clean validation data. The proposed framework first utilizes the memorization effect of CNNs to learn a curriculum, which contains confident samples and provides meaningful supervision for other training samples. Then it adopts selected confident samples and a proposed resistance loss to update model parameters; the resistance loss tends to smooth model parameters' update or attain equivalent prediction over each class, thereby resisting model overfitting on corrupted labels. Finally, we unify these two modules into a single loss function and optimize it in an alternative learning. Extensive experiments demonstrate the significantly superior performance of the proposed framework over recent state-of-the-art methods on noisy-label data. Source codes of the proposed method are available on https://github.com/xsshi2015/Self-paced-Resistance-Learning.