Co-matching: Combating Noisy Labels by Augmentation Anchoring

Abstract

Deep learning with noisy labels is challenging as deep neural networks have the high capacity to memorize the noisy labels. In this paper, we propose a learning algorithm called Co-matching, which balances the consistency and divergence between two networks by augmentation anchoring. Specifically, we have one network generate anchoring label from its prediction on a weakly-augmented image. Meanwhile, we force its peer network, taking the strongly-augmented version of the same image as input, to generate prediction close to the anchoring label. We then update two networks simultaneously by selecting small-loss instances to minimize both unsupervised matching loss (i.e., measure the consistency of the two networks) and supervised classification loss (i.e. measure the classification performance). Besides, the unsupervised matching loss makes our method not heavily rely on noisy labels, which prevents memorization of noisy labels. Experiments on three benchmark datasets demonstrate that Co-matching achieves results comparable to the state-of-the-art methods.

13 pages, 10 figures. arXiv admin note: text overlap with arXiv:2003.02752 by other authors

References in corpus (10)

• Temporal Ensembling for Semi-Supervised Learning
• Understanding deep learning requires rethinking generalization
• Training Deep Neural Networks on Noisy Labels with Bootstrapping
• Training Convolutional Networks with Noisy Labels
• DivideMix: Learning with Noisy Labels as Semi-supervised Learning
• Learning with Pseudo-Ensembles
• WebVision Database: Visual Learning and Understanding from Web Data
• Unsupervised Label Noise Modeling and Loss Correction
• ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring
• Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels