{
  "id": "2003.13216",
  "version": "v1",
  "published": "2020-03-30T04:39:53.000Z",
  "updated": "2020-03-30T04:39:53.000Z",
  "title": "Learning to Learn Single Domain Generalization",
  "authors": [
    "Fengchun Qiao",
    "Long Zhao",
    "Xi Peng"
  ],
  "comment": "In CVPR 2020 (13 pages including supplementary material). The source code and pre-trained models are publicly available at: https://github.com/joffery/M-ADA",
  "categories": [
    "cs.CV"
  ],
  "abstract": "We are concerned with a worst-case scenario in model generalization, in the sense that a model aims to perform well on many unseen domains while there is only one single domain available for training. We propose a new method named adversarial domain augmentation to solve this Out-of-Distribution (OOD) generalization problem. The key idea is to leverage adversarial training to create \"fictitious\" yet \"challenging\" populations, from which a model can learn to generalize with theoretical guarantees. To facilitate fast and desirable domain augmentation, we cast the model training in a meta-learning scheme and use a Wasserstein Auto-Encoder (WAE) to relax the widely used worst-case constraint. Detailed theoretical analysis is provided to testify our formulation, while extensive experiments on multiple benchmark datasets indicate its superior performance in tackling single domain generalization.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2020-03-30T04:39:53.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "learn single domain generalization",
      "method named adversarial domain augmentation",
      "tackling single domain generalization",
      "multiple benchmark datasets",
      "desirable domain augmentation"
    ],
    "tags": [
      "github project"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 13,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}