{
  "id": "1902.04552",
  "version": "v1",
  "published": "2019-02-12T18:55:18.000Z",
  "updated": "2019-02-12T18:55:18.000Z",
  "title": "Infinite Mixture Prototypes for Few-Shot Learning",
  "authors": [
    "Kelsey R. Allen",
    "Evan Shelhamer",
    "Hanul Shin",
    "Joshua B. Tenenbaum"
  ],
  "categories": [
    "cs.LG",
    "stat.ML"
  ],
  "abstract": "We propose infinite mixture prototypes to adaptively represent both simple and complex data distributions for few-shot learning. Our infinite mixture prototypes represent each class by a set of clusters, unlike existing prototypical methods that represent each class by a single cluster. By inferring the number of clusters, infinite mixture prototypes interpolate between nearest neighbor and prototypical representations, which improves accuracy and robustness in the few-shot regime. We show the importance of adaptive capacity for capturing complex data distributions such as alphabets, with 25% absolute accuracy improvements over prototypical networks, while still maintaining or improving accuracy on the standard Omniglot and mini-ImageNet benchmarks. In clustering labeled and unlabeled data by the same clustering rule, infinite mixture prototypes achieves state-of-the-art semi-supervised accuracy. As a further capability, we show that infinite mixture prototypes can perform purely unsupervised clustering, unlike existing prototypical methods.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2019-02-12T18:55:18.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "few-shot learning",
      "achieves state-of-the-art semi-supervised accuracy",
      "complex data distributions",
      "infinite mixture prototypes achieves state-of-the-art",
      "unlike existing prototypical methods"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}