{
  "id": "1606.04189",
  "version": "v1",
  "published": "2016-06-14T01:35:12.000Z",
  "updated": "2016-06-14T01:35:12.000Z",
  "title": "Inverting face embeddings with convolutional neural networks",
  "authors": [
    "Andrey Zhmoginov",
    "Mark Sandler"
  ],
  "categories": [
    "cs.CV",
    "cs.LG",
    "cs.NE"
  ],
  "abstract": "Deep neural networks have dramatically advanced the state of the art for many areas of machine learning. Recently they have been shown to have a remarkable ability to generate highly complex visual artifacts such as images and text rather than simply recognize them. In this work we use neural networks to effectively invert low-dimensional face embeddings while producing realistically looking consistent images. Our contribution is twofold, first we show that a gradient ascent style approaches can be used to reproduce consistent images, with a help of a guiding image. Second, we demonstrate that we can train a separate neural network to effectively solve the minimization problem in one pass, and generate images in real-time. We then evaluate the loss imposed by using a neural network instead of the gradient descent by comparing the final values of the minimized loss function.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2016-06-14T01:35:12.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "convolutional neural networks",
      "inverting face embeddings",
      "invert low-dimensional face embeddings",
      "realistically looking consistent images",
      "generate highly complex visual artifacts"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}