Keywords: Learning with noisy labels, Sample selection, Uncertainty
Abstract: In learning with noisy labels, the sample selection approach is very popular, which regards small-loss data as correctly labeled data during training. However, losses are generated on-the-ﬂy based on the model being trained with noisy labels, and thus large-loss data are likely but not certain to be incorrect. There are actually two possibilities of a large-loss data point: (a) it is mislabeled, and then its loss decreases slower than other data, since deep neural networks learn patterns ﬁrst; (b) it belongs to an underrepresented group of data and has not been selected yet. In this paper, we incorporate the uncertainty of losses by adopting interval estimation instead of point estimation of losses, where lower bounds of the conﬁdence intervals of losses derived from distribution-free concentration inequalities, but not losses themselves, are used for sample selection. In this way, we also give large-loss but less selected data a try; then, we can better distinguish between the cases (a) and (b) by seeing if the losses effectively decrease with the uncertainty after the try. As a result, we can better explore underrepresented data that are correctly labeled but seem to be mislabeled at ﬁrst glance. Experiments demonstrate that the proposed method is superior to baselines and robust to a broad range of label noise types.
Supplementary Material: zip