{
  "id": "1605.07270",
  "version": "v1",
  "published": "2016-05-24T02:42:53.000Z",
  "updated": "2016-05-24T02:42:53.000Z",
  "title": "Learning a Metric Embedding for Face Recognition using the Multibatch Method",
  "authors": [
    "Oren Tadmor",
    "Yonatan Wexler",
    "Tal Rosenwein",
    "Shai Shalev-Shwartz",
    "Amnon Shashua"
  ],
  "categories": [
    "cs.CV"
  ],
  "abstract": "This work is motivated by the engineering task of achieving a near state-of-the-art face recognition on a minimal computing budget running on an embedded system. Our main technical contribution centers around a novel training method, called Multibatch, for similarity learning, i.e., for the task of generating an invariant \"face signature\" through training pairs of \"same\" and \"not-same\" face images. The Multibatch method first generates signatures for a mini-batch of $k$ face images and then constructs an unbiased estimate of the full gradient by relying on all $k^2-k$ pairs from the mini-batch. We prove that the variance of the Multibatch estimator is bounded by $O(1/k^2)$, under some mild conditions. In contrast, the standard gradient estimator that relies on random $k/2$ pairs has a variance of order $1/k$. The smaller variance of the Multibatch estimator significantly speeds up the convergence rate of stochastic gradient descent. Using the Multibatch method we train a deep convolutional neural network that achieves an accuracy of $98.2\\%$ on the LFW benchmark, while its prediction runtime takes only $30$msec on a single ARM Cortex A9 core. Furthermore, the entire training process took only 12 hours on a single Titan X GPU.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2016-05-24T02:42:53.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "face recognition",
      "metric embedding",
      "single arm cortex a9 core",
      "multibatch method first generates signatures",
      "multibatch estimator"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}