{
  "id": "2205.15781",
  "version": "v1",
  "published": "2022-05-31T13:30:36.000Z",
  "updated": "2022-05-31T13:30:36.000Z",
  "title": "Co-Training for Unsupervised Domain Adaptation of Semantic Segmentation Models",
  "authors": [
    "Jose L. Gómez",
    "Gabriel Villalonga",
    "Antonio M. López"
  ],
  "categories": [
    "cs.CV"
  ],
  "abstract": "Semantic image segmentation is addressed by training deep models. Since supervised training draws to a curse of human-based image labeling, using synthetic images with automatically generated ground truth together with unlabeled real-world images is a promising alternative. This implies to address an unsupervised domain adaptation (UDA) problem. In this paper, we proposed a new co-training process for synth-to-real UDA of semantic segmentation models. First, we design a self-training procedure which provides two initial models. Then, we keep training these models in a collaborative manner for obtaining the final model. The overall process treats the deep models as black boxes and drives their collaboration at the level of pseudo-labeled target images, {\\ie}, neither modifying loss functions is required, nor explicit feature alignment. We test our proposal on standard synthetic and real-world datasets. Our co-training shows improvements of 15-20 percentage points of mIoU over baselines, so establishing new state-of-the-art results.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2022-05-31T13:30:36.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "semantic segmentation models",
      "unsupervised domain adaptation",
      "co-training",
      "deep models",
      "semantic image segmentation"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}