Open-Sampling: Exploring Out-of-Distribution data for Re-balancing Long-tailed datasets. (arXiv:2206.08802v2 [cs.LG] UPDATED)

Deep neural networks usually perform poorly when the training dataset suffers
from extreme class imbalance. Recent studies found that directly training with
out-of-distribution data (i.e., open-set samples) in a semi-supervised manner
would harm the generalization performance. In this work, we theoretically show
that out-of-distribution data can still be leveraged to augment the minority
classes from a Bayesian perspective. Based on this motivation, we propose a
novel method called Open-sampling, which utilizes open-set noisy labels to
re-balance the class priors of …

arxiv data datasets distribution lg sampling