Learning Multi-Level Consistency for Noisy Labels

Recent methods performing well on Learning with Noisy Label (LNL) problem generally are based on semi-supervised learning and consistency regularization. It usually consists of three stages: warm-up, noisy/clean data division, and semi-supervised learning. However, these methods trained purely with classification consistency suffer from the confirmation bias problem and tend to memorize the noisy labels, resulting in accumulated error and degraded performance. Leveraging the compositional and relational peculiarities of the noisy data, we propose a graph-based Multi-Level Consistency (MLC) framework that jointly exploits multi-level relation consistencies between graphs and classification consistency which can better correct wrong labels by continuing to learn the multi-level differences between clean data and noisy data. Moreover, we propose a Dynamic Filter Module (DFM) which effectively improves the reliability of divided data by re-filtering noisy data despite its simplicity. Our method achieves the stateof-the-art performance on multiple benchmark datasets. On Cifar-100 with 90% noisy labels, our method achieves a top-1 accuracy of 49.1%, outperforming DivideMix by 17.6%.