Fix-A-Step: Effective Semi-supervised Learning from Uncurated Unlabeled Sets. (arXiv:2208.11870v1 [cs.LG])

Semi-supervised learning (SSL) promises gains in accuracy compared to
training classifiers on small labeled datasets by also training on many
unlabeled images. In realistic applications like medical imaging, unlabeled
sets will be collected for expediency and thus uncurated: possibly different
from the labeled set in represented classes or class frequencies.
Unfortunately, modern deep SSL often makes accuracy worse when given uncurated
unlabeled sets. Recent remedies suggest filtering approaches that detect
out-of-distribution unlabeled examples and then discard or downweight them.
Instead, …

arxiv learning lg semi-supervised semi-supervised learning supervised learning