{
  "id": "1911.09785",
  "version": "v1",
  "published": "2019-11-21T23:44:25.000Z",
  "updated": "2019-11-21T23:44:25.000Z",
  "title": "ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring",
  "authors": [
    "David Berthelot",
    "Nicholas Carlini",
    "Ekin D. Cubuk",
    "Alex Kurakin",
    "Kihyuk Sohn",
    "Han Zhang",
    "Colin Raffel"
  ],
  "categories": [
    "cs.LG",
    "cs.AI",
    "cs.CV",
    "stat.ML"
  ],
  "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.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2019-11-21T23:44:25.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "semi-supervised learning",
      "remixmatch",
      "marginal distribution",
      "feeds multiple strongly augmented versions",
      "augmentation anchoring feeds multiple"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}