{
  "id": "1611.08998",
  "version": "v1",
  "published": "2016-11-28T06:42:56.000Z",
  "updated": "2016-11-28T06:42:56.000Z",
  "title": "DeepSetNet: Predicting Sets with Deep Neural Networks",
  "authors": [
    "Seyed Hamid Rezatofighi",
    "Vijay Kumar B G",
    "Anton Milan",
    "Ehsan Abbasnejad",
    "Anthony Dick",
    "Ian Reid"
  ],
  "categories": [
    "cs.CV",
    "cs.AI",
    "cs.LG"
  ],
  "abstract": "This paper addresses the task of set prediction using deep learning. This is important because the output of many computer vision tasks, including image tagging and object detection, are naturally expressed as sets of entities rather than vectors. As opposed to a vector, the size of a set is not fixed in advance, and it is invariant to the ordering of entities within it. We define a likelihood for a set distribution and learn its parameters using a deep neural network. We also derive a loss for predicting a discrete distribution corresponding to set cardinality. Set prediction is demonstrated on the problems of multi-class image classification and pedestrian detection. Our approach yields state-of-the-art results in both cases on standard datasets.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2016-11-28T06:42:56.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "deep neural network",
      "predicting sets",
      "set prediction",
      "deepsetnet",
      "approach yields state-of-the-art results"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}