2020/03/26 by Geoff French, French, Geoff, Avital Oliver +3 · 1 citation
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #cs.CV
paper · pdf · doi:10.48550/arxiv.2003.12022
11 pages, 2 figures, submitted to NeurIPS 2020
arxiv created 2020/06/05 · arxiv updated 2020/06/09
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 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%. 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/milkingcowmask