ReMixMatch: Semi-Supervised Learning with Distribution Matching and Augmentation Anchoring

David Berthelot, Nicholas Carlini, Ekin D. Cubuk, Alex Kurakin, Kihyuk Sohn, Han Zhang, Colin Raffel

Keywords: semi-supervised learning

TL;DR: We introduce Distribution Matching and Augmentation Anchoring, two improvements to MixMatch which produce state-of-the-art results and enable surprisingly strong performance with only 40 labels on CIFAR-10 and SVHN.

Abstract:

We improve the recently-proposed ``MixMatch semi-supervised learning algorithm by introducing two new techniques: distribution alignment and augmentation anchoring.
- Distribution alignment encourages the marginal distribution of predictions on unlabeled data to be close to the marginal distribution of ground-truth labels.
- Augmentation anchoring} feeds multiple strongly augmented versions of an input into the model and encourages each output to be close to the prediction for a weakly-augmented version of the same input.
To produce strong augmentations, we propose a variant of AutoAugment which learns the augmentation policy while the model is being trained.

Our new algorithm, dubbed ReMixMatch, is significantly more data-efficient than prior work, requiring between 5 times and 16 times less data to reach the same accuracy. For example, on CIFAR-10 with 250 labeled examples we reach 93.73% accuracy (compared to MixMatch's accuracy of 93.58% with 4000 examples) and a median accuracy of 84.92% with just four labels per class.

Code: https://github.com/google-research/remixmatch