← Search

Laura Beggel

1 accepted papers

2020

SELF: Learning to Filter Noisy Labels with Self-Ensembling

ICLR 2020poster

Deep neural networks (DNNs) have been shown to over-fit a dataset when being trained with noisy labels for a long enough time. To overcome this problem, we present a simple and effective method self-ensemble label filtering (SELF) to progressively filter out the wrong labels during training. Our met…

Cited by 400SourceScholar