Authors:
Geoff French
1
;
2
;
Avital Oliver
1
and
Tim Salimans
1
Affiliations:
1
Google Research, Brain Team, Amsterdam, The Netherlands
;
2
School of Computing Sciences, University of East Anglia, Norwich, U.K.
Keyword(s):
Semi-supervised Learning, Image Classification, Deep Learning.
Abstract:
Consistency regularization is a technique for semi-supervised learning that underlies a number of strong results for classification with few labeled data. It works by encouraging a learned model to be robust to perturbations on unlabeled data. Here, we present a novel mask-based augmentation method called CowMask. Using it to provide perturbations for semi-supervised consistency regularization, we achieve a competitive result on ImageNet with 10% labeled data, with a top-5 error of 8.76% and top-1 error of 26.06%. Moreover, we do so with a method that is much simpler than many alternatives. We further investigate the behavior of CowMask for semi-supervised learning by running many smaller scale experiments on the SVHN, CIFAR-10 and CIFAR-100 data sets, where we achieve results competitive with the state of the art, indicating that CowMask is widely applicable. We open source our code at https://github.com/google-research/google-research/tree/master/milking cowmask.