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

Abstract: 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.