DeepAI AI Chat
Log In Sign Up

Unsupervised label noise modeling and loss correction

by   Eric Arazo, et al.

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


page 1

page 2

page 3

page 4


Synergistic Network Learning and Label Correction for Noise-robust Image Classification

Large training datasets almost always contain examples with inaccurate o...

CrossSplit: Mitigating Label Noise Memorization through Data Splitting

We approach the problem of improving robustness of deep learning algorit...

Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach

We present a theoretically grounded approach to train deep neural networ...

Noise-Robust Bidirectional Learning with Dynamic Sample Reweighting

Deep neural networks trained with standard cross-entropy loss are more p...

Label Embedding Network: Learning Label Representation for Soft Training of Deep Networks

We propose a method, called Label Embedding Network, which can learn lab...

Learning to Bootstrap for Combating Label Noise

Deep neural networks are powerful tools for representation learning, but...

ProSelfLC: Progressive Self Label Correction Towards A Low-Temperature Entropy State

To train robust deep neural networks (DNNs), we systematically study sev...

Code Repositories


Official Implementation of ICML 2019 Unsupervised label noise modeling and loss correction

view repo