{
  "id": "1902.09884",
  "version": "v1",
  "published": "2019-02-26T12:16:10.000Z",
  "updated": "2019-02-26T12:16:10.000Z",
  "title": "Assume, Augment and Learn: Unsupervised Few-Shot Meta-Learning via Random Labels and Data Augmentation",
  "authors": [
    "Antreas Antoniou",
    "Amos Storkey"
  ],
  "comment": "Work in Progress - Under Review in ICML 2019",
  "categories": [
    "stat.ML",
    "cs.LG"
  ],
  "abstract": "The field of few-shot learning has been laboriously explored in the supervised setting, where per-class labels are available. On the other hand, the unsupervised few-shot learning setting, where no labels of any kind are required, has seen little investigation. We propose a method, named Assume, Augment and Learn or AAL, for generating few-shot tasks using unlabeled data. We randomly label a random subset of images from an unlabeled dataset to generate a support set. Then by applying data augmentation on the support set's images, and reusing the support set's labels, we obtain a target set. The resulting few-shot tasks can be used to train any standard meta-learning framework. Once trained, such a model, can be directly applied on small real-labeled datasets without any changes or fine-tuning required. In our experiments, the learned models achieve good generalization performance in a variety of established few-shot learning tasks on Omniglot and Mini-Imagenet.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2019-02-26T12:16:10.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "data augmentation",
      "unsupervised few-shot meta-learning",
      "random labels",
      "few-shot tasks",
      "support sets labels"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}