Ensemble noisy label detection on MNIST

Fazekas, István and Barta, Attila and Fórián, László (2021) Ensemble noisy label detection on MNIST. Annales Mathematicae et Informaticae, 53. pp. 125-137. ISSN 1787-6117

Preview

Text AMI_53_from125to137.pdf - Published Version Download (805kB) | Preview

Abstract

In this paper machine learning methods are studied for classification data containing some misleading items. We use ensembles of known noise correction methods for preprocessing the training set. Preprocessing can be either relabeling or deleting items detected to have noisy labels. After preprocessing, usual convolutional networks are applied to the data. With preprocessing, the performance of very accurate convolutional networks can be further improved.

Actions (login required)

Edit Item