{
  "id": "2211.16488",
  "version": "v1",
  "published": "2022-11-29T18:56:04.000Z",
  "updated": "2022-11-29T18:56:04.000Z",
  "title": "Taming a Generative Model",
  "authors": [
    "Shimon Malnick",
    "Shai Avidan",
    "Ohad Fried"
  ],
  "categories": [
    "cs.CV"
  ],
  "abstract": "Generative models are becoming ever more powerful, being able to synthesize highly realistic images. We propose an algorithm for taming these models - changing the probability that the model will produce a specific image or image category. We consider generative models that are powered by normalizing flows, which allows us to reason about the exact generation probability likelihood for a given image. Our method is general purpose, and we exemplify it using models that generate human faces, a subdomain with many interesting privacy and bias considerations. Our method can be used in the context of privacy, e.g., removing a specific person from the output of a model, and also in the context of de-biasing by forcing a model to output specific image categories according to a given target distribution. Our method uses a fast fine-tuning process without retraining the model from scratch, achieving the goal in less than 1% of the time taken to initially train the generative model. We evaluate qualitatively and quantitatively, to examine the success of the taming process and output quality.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2022-11-29T18:56:04.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "generative model",
      "output specific image categories",
      "exact generation probability likelihood",
      "image category",
      "generate human faces"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}