{
  "id": "1505.02146",
  "version": "v1",
  "published": "2015-05-08T19:24:17.000Z",
  "updated": "2015-05-08T19:24:17.000Z",
  "title": "DeepBox: Learning Objectness with Convolutional Networks",
  "authors": [
    "Weicheng Kuo",
    "Bharath Hariharan",
    "Jitendra Malik"
  ],
  "categories": [
    "cs.CV"
  ],
  "abstract": "Existing object proposal approaches use primarily bottom-up cues to rank proposals, while we believe that objectness is in fact a high level construct. We argue for a data-driven, semantic approach for ranking object proposals. Our framework, which we call DeepBox, uses convolutional neural networks (CNNs) to rerank proposals from a bottom-up method. We use a novel four-layer CNN architecture that is as good as much larger networks on the task of evaluating objectness while being much faster. We show that DeepBox significantly improves over the bottom-up ranking, achieving the same recall with 500 proposals as achieved by bottom-up methods with 2000. This improvement generalizes to categories the CNN has never seen before. Finally, DeepBox has a significant impact on the performance of the object detector, reducing by 40% the total time taken for detection.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2015-05-08T19:24:17.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "convolutional networks",
      "learning objectness",
      "novel four-layer cnn architecture",
      "bottom-up method",
      "convolutional neural networks"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable",
      "adsabs": "2015arXiv150502146K"
    }
  }
}