Consistency regularization describes a class of approaches that have yielded state-of-the-art results for semi-supervised classification.
Using it to provide perturbations for semi-supervised consistency regularization, we achieve a state-of-the-art result on ImageNet with 10% labeled data, with a top-5 error of 8. 76% and top-1 error of 26. 06%.
Consistency regularization describes a class of approaches that have yielded ground breaking results in semi-supervised classification problems.
We analyze the problem of semantic segmentation and find that its' distribution does not exhibit low density regions separating classes and offer this as an explanation for why semi-supervised segmentation is a challenging problem, with only a few reports of success.