Combating Noisy-Labeled and Imbalanced Data by Two Stage Bi-Dimensional Sample Selection. (arXiv:2208.09833v1 [cs.LG])

Robust learning on noisy-labeled data has been an important task in real
applications, because label noise directly leads to the poor generalization of
deep learning models. Existing label-noise learning methods usually assume that
the ground-truth classes of the training data are balanced. However, the
real-world data is often imbalanced, leading to the inconsistency between
observed and intrinsic class distribution due to label noises. Distribution
inconsistency makes the problem of label-noise learning more challenging
because it is hard to distinguish clean …

arxiv bi data lg stage