{
  "id": "1802.03596",
  "version": "v1",
  "published": "2018-02-10T14:18:08.000Z",
  "updated": "2018-02-10T14:18:08.000Z",
  "title": "Deep Meta-Learning: Learning to Learn in the Concept Space",
  "authors": [
    "Fengwei Zhou",
    "Bin Wu",
    "Zhenguo Li"
  ],
  "categories": [
    "cs.LG"
  ],
  "abstract": "Few-shot learning remains challenging for meta-learning that learns a learning algorithm (meta-learner) from many related tasks. In this work, we argue that this is due to the lack of a good representation for meta-learning, and propose deep meta-learning to integrate the representation power of deep learning into meta-learning. The framework is composed of three modules, a concept generator, a meta-learner, and a concept discriminator, which are learned jointly. The concept generator, e.g. a deep residual net, extracts a representation for each instance that captures its high-level concept, on which the meta-learner performs few-shot learning, and the concept discriminator recognizes the concepts. By learning to learn in the concept space rather than in the complicated instance space, deep meta-learning can substantially improve vanilla meta-learning, which is demonstrated on various few-shot image recognition problems. For example, on 5-way-1-shot image recognition on CIFAR-100 and CUB-200, it improves Matching Nets from 50.53% and 56.53% to 58.18% and 63.47%, improves MAML from 49.28% and 50.45% to 56.65% and 64.63%, and improves Meta-SGD from 53.83% and 53.34% to 61.62% and 66.95%, respectively.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2018-02-10T14:18:08.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "concept space",
      "deep meta-learning",
      "concept generator",
      "few-shot image recognition problems",
      "deep residual net"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}