{
  "id": "1510.08160",
  "version": "v1",
  "published": "2015-10-28T01:59:14.000Z",
  "updated": "2015-10-28T01:59:14.000Z",
  "title": "Scale-aware Fast R-CNN for Pedestrian Detection",
  "authors": [
    "Jianan Li",
    "Xiaodan Liang",
    "ShengMei Shen",
    "Tingfa Xu",
    "Shuicheng Yan"
  ],
  "categories": [
    "cs.CV"
  ],
  "abstract": "While convolutional neural network (CNN) architectures have achieved great success in various vision tasks, the critical scale problem is still much under-explored, especially for pedestrian detection. Current approaches mainly focus on using large numbers of training images with different scales to improve the network capability or result fusions by multi-scale crops of images during testing. Designing a CNN architecture that can intrinsically capture the characteristics of large-scale and small-scale objects and also retain the scale invariance property is still a very challenging problem. In this paper, we propose a novel scale-aware Fast R-CNN to handle the detection of small object instances which are very common in pedestrian detection. Our architecture incorporates a large-scale sub-network and a small-scale sub-network into a unified architecture by leveraging the scale-aware weighting during training. The heights of object proposals are utilized to specify different scale-aware weights for the two sub-networks. Extensive evaluations on the challenging Caltech~\\cite{dollar2012pedestrian} demonstrate the superiority of the proposed architecture over the state-of-the-art methods~\\cite{compact,ta_cnn}. In particular, the miss rate on the Caltech dataset is reduced to $9.68\\%$ by our method, significantly smaller than $11.75\\%$ by CompACT-Deep~\\cite{compact} and $20.86\\%$ by TA-CNN~\\cite{ta_cnn}.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2015-10-28T01:59:14.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "pedestrian detection",
      "architecture",
      "novel scale-aware fast r-cnn",
      "sub-network",
      "convolutional neural network"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable",
      "adsabs": "2015arXiv151008160L"
    }
  }
}