Abstract
Supervised deep learning methods require a large repository of annotated data; hence, label noise is inevitable. Training with such noisy data negatively impacts the generalization performance of deep neural networks. To combat label noise, recent state-of-the-art methods employ some sort of sample selection mechanism to select a possibly clean subset of data. Next, an off-the-shelf semi-supervised learning method is used for training where rejected samples are treated as unlabeled data. Our comprehensive analysis shows that current selection methods disproportionately select samples from easy (fast learnable) classes while reject those from relatively harder ones. This creates class imbalance in the selected clean set and in turn deteriorates performance under high label noise. In this work, we propose UNICON, a simple yet effective sample selection method which is robust to high label noise. To address the disproportionate selection of easy and hard samples, we introduce a Jensen-Shannon divergence based uniform selection mechanism which does not require any probabilistic modelling and hyperparameter tuning. We complement our selection method with contrastive learning to further combat memorization of noisy labels. Extensive experimentation on multiple benchmark datasets demonstrate the effectiveness of UNICON; we obtain 11.4% improvement over the current state-of-the-art on CIFAR100 dataset with 90% noise rate.
Abstract (translated)
URL
https://arxiv.org/abs/2203.14542
