Uncertainty Based Detection and Relabeling of Noisy Image Labels

Jan M. Kohler, Maximilian Autenrieth, William H. Beluch; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2019, pp. 33-37

Abstract


Deep neural networks (DNNs) are powerful tools in computer vision tasks. However, in many realistic scenarios label noise is prevalent in the training images, and overfitting to these noisy labels can significantly harm the generalization performance of DNNs. We propose a novel technique to identify data with noisy labels based on the different distributions of the predictive uncertainties from a DNN over the clean and noisy data. Additionally, the behavior of the uncertainty over the course of training helps to identify the network weights which best can be used to re- label the noisy labels. Data with noisy labels can therefore be cleaned in an iterative process. Our proposed method can be easily implemented, and shows promising performance on the task of noisy label detection on CIFAR-10 and CIFAR-100.

Related Material


[pdf]
[bibtex]
@InProceedings{Kohler_2019_CVPR_Workshops,
author = {Kohler, Jan M. and Autenrieth, Maximilian and Beluch, William H.},
title = {Uncertainty Based Detection and Relabeling of Noisy Image Labels},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2019}
}