Skip to yearly menu bar Skip to main content


Unsupervised Label Noise Modeling and Loss Correction

Eric Arazo · Diego Ortego · Paul Albert · Noel O'Connor · Kevin McGuinness

Pacific Ballroom #176

Keywords: [ Unsupervised and Semi-supervised Learning ] [ Computer Vision ]


Despite being robust to small amounts of label noise, convolutional neural networks trained with stochastic gradient methods have been shown to easily fit random labels. When there are a mixture of correct and mislabelled targets, networks tend to fit the former before the latter. This suggests using a suitable two-component mixture model as an unsupervised generative model of sample loss values during training to allow online estimation of the probability that a sample is mislabelled. Specifically, we propose a beta mixture to estimate this probability and correct the loss by relying on the network prediction (the so-called bootstrapping loss). We further adapt mixup augmentation to drive our approach a step further. Experiments on CIFAR-10/100 and TinyImageNet demonstrate a robustness to label noise that substantially outperforms recent state-of-the-art. Source code is available at and Appendix at

Live content is unavailable. Log in and register to view live content