{
  "id": "2002.04274",
  "version": "v1",
  "published": "2020-02-11T09:25:13.000Z",
  "updated": "2020-02-11T09:25:13.000Z",
  "title": "Meta-Learning across Meta-Tasks for Few-Shot Learning",
  "authors": [
    "Nanyi Fei",
    "Zhiwu Lu",
    "Yizhao Gao",
    "Jia Tian",
    "Tao Xiang",
    "Ji-Rong Wen"
  ],
  "categories": [
    "cs.LG",
    "stat.ML"
  ],
  "abstract": "Existing meta-learning based few-shot learning (FSL) methods typically adopt an episodic training strategy whereby each episode contains a meta-task. Across episodes, these tasks are sampled randomly and their relationships are ignored. In this paper, we argue that the inter-meta-task relationships should be exploited to learn models that are more generalizable to unseen classes with few-shots. Specifically, we consider the relationships between two types of meta-tasks and propose different strategies to exploit them. (1) Two meta-tasks with disjoint sets of classes: these are interesting because their relationship is reminiscent of that between the source seen classes and target unseen classes, featured with domain gap caused by class differences. A novel meta-training strategy named meta-domain adaptation (MDA) is proposed to make the meta-learned model more robust to the domain gap. (2) Two meta-tasks with identical sets of classes: these are interesting because they can be used to learn models that are robust against poorly sampled few-shots. To that end, a novel meta-knowledge distillation (MKD) strategy is formulated. Extensive experiments demonstrate that both MDA and MKD significantly boost the performance of a variety of existing FSL methods and thus achieve new state-of-the-art on three benchmarks.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2020-02-11T09:25:13.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "few-shot learning",
      "domain gap",
      "relationship",
      "learn models",
      "target unseen classes"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}