ReMixMatch swMATH ID: 41275 Software Authors: David Berthelot, Nicholas Carlini, Ekin D. Cubuk, Alex Kurakin, Kihyuk Sohn, Han Zhang, Colin Raffel Description: ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring. 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× and 16× less data to reach the same accuracy. For example, on CIFAR-10 with 250 labeled examples we reach 93.73 Homepage: https://arxiv.org/abs/1911.09785 Source Code: https://github.com/google-research/remixmatch Dependencies: Python Related Software: FixMatch; MixMatch; Python; Scikit; PyTorch; FlexMatch; S4L; RandAugment; SGDR; ImageNet; CIFAR; SemiBoost; LAMDA-SSL; AutoAugment; AugMix; Adam; TADAM; SpecAugment; mixup; LargeVis Cited in: 1 Document Cited by 3 Authors 1 Gentner, Timothy Q. 1 McInnes, Leland 1 Sainburg, Tim Cited in 1 Serial 1 Neural Computation Cited in 1 Field 1 Computer science (68-XX) Citations by Year