{
  "id": "1711.11556",
  "version": "v1",
  "published": "2017-11-30T18:22:30.000Z",
  "updated": "2017-11-30T18:22:30.000Z",
  "title": "ROAD: Reality Oriented Adaptation for Semantic Segmentation of Urban Scenes",
  "authors": [
    "Yuhua Chen",
    "Wen Li",
    "Luc Van Gool"
  ],
  "categories": [
    "cs.CV"
  ],
  "abstract": "Exploiting synthetic data to learn deep models has attracted increasing attention in recent years. However, the intrinsic domain difference between synthetic and real images usually causes a significant performance drop when applying the learned model to real world scenarios. This is mainly due to two reasons: 1) the model overfits to synthetic images, making the convolutional filters incompetent to extract informative representation for real images; 2) there is a distribution difference between synthetic and real data, which is also known as the domain adaptation problem. To this end, we propose a new reality oriented adaptation approach for urban scene semantic segmentation by learning from synthetic data. First, we propose a target guided distillation approach to learn the real image style, which is achieved by training the segmentation model to imitate a pretrained real style model using real images. Second, we further take advantage of the intrinsic spatial structure presented in urban scene images, and propose a spatial-aware adaptation scheme to effectively align the distribution of two domains. These two components can be readily integrated into existing state-of-the-art semantic segmentation networks to improve their generalizability when adapting from synthetic to real urban scenes. We achieve a new state-of-the-art of 39.4% mean IoU on the Cityscapes dataset by adapting from the GTAV dataset.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2017-11-30T18:22:30.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "reality oriented adaptation",
      "real image",
      "synthetic data",
      "urban scene semantic segmentation",
      "existing state-of-the-art semantic segmentation networks"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}