Robust training with ensemble consensusDownload PDF

Published: 20 Dec 2019, Last Modified: 22 Oct 2023ICLR 2020 Conference Blind SubmissionReaders: Everyone
Keywords: Annotation noise, Noisy label, Robustness, Ensemble, Perturbation
TL;DR: This work presents a method to robustly train neural networks by using ensemble in the presence of label noise.
Abstract: Since deep neural networks are over-parameterized, they can memorize noisy examples. We address such a memorization issue in the presence of label noise. From the fact that deep neural networks cannot generalize to neighborhoods of memorized features, we hypothesize that noisy examples do not consistently incur small losses on the network under a certain perturbation. Based on this, we propose a novel training method called Learning with Ensemble Consensus (LEC) that prevents overfitting to noisy examples by removing them based on the consensus of an ensemble of perturbed networks. One of the proposed LECs, LTEC outperforms the current state-of-the-art methods on noisy MNIST, CIFAR-10, and CIFAR-100 in an efficient manner.
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](
Original Pdf: pdf
10 Replies