@analyst

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

, , , , , , and . (2019)cite arxiv:1911.09785.

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 $4,000$ examples) and a median accuracy of $84.92\%$ with just four labels per class. We make our code and data open-source at https://github.com/google-research/remixmatch.

Description

[1911.09785] ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring

Links and resources

URL:
additional links:
BibTeX key:
berthelot2019remixmatch
search on:

Comments and Reviews  
(0)

There is no review or comment yet. You can write one!

Tags


Cite this publication