{
  "id": "1711.08875",
  "version": "v1",
  "published": "2017-11-24T06:04:02.000Z",
  "updated": "2017-11-24T06:04:02.000Z",
  "title": "Wasserstein Introspective Neural Networks",
  "authors": [
    "Kwonjoon Lee",
    "Weijian Xu",
    "Fan Fan",
    "Zhuowen Tu"
  ],
  "comment": "Submitted to CVPR 2018",
  "categories": [
    "cs.CV"
  ],
  "abstract": "We present Wasserstein introspective neural networks (WINN) that are both a generator and a discriminator within a single model. WINN provides a significant improvement over the recent introspective neural networks (INN) method by enhancing INN's generative modeling capability. WINN has three interesting properties: (1) A mathematical connection between the formulation of Wasserstein generative adversarial networks (WGAN) and the INN algorithm is made; (2) The explicit adoption of the WGAN term into INN results in a large enhancement to INN, achieving compelling results even with a single classifier on e.g., providing a 20 times reduction in model size over INN within texture modeling; (3) When applied to supervised classification, WINN also gives rise to greater robustness with an $88\\%$ reduction of errors against adversarial examples -- improved over the result of $39\\%$ by an INN-family algorithm. In the experiments, we report encouraging results on unsupervised learning problems including texture, face, and object modeling, as well as a supervised classification task against adversarial attack.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2017-11-24T06:04:02.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "wasserstein introspective neural networks",
      "supervised classification",
      "wasserstein generative adversarial networks",
      "adversarial examples",
      "enhancing inns generative modeling capability"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}