{
  "id": "1707.06426",
  "version": "v1",
  "published": "2017-07-20T09:45:08.000Z",
  "updated": "2017-07-20T09:45:08.000Z",
  "title": "Semantic Segmentation with Reverse Attention",
  "authors": [
    "Qin Huang",
    "Chunyang Xia",
    "Chihao Wu",
    "Siyang Li",
    "Ye Wang",
    "Yuhang Song",
    "C. -C. Jay Kuo"
  ],
  "comment": "accepted for oral presentation in BMVC 2017",
  "categories": [
    "cs.CV"
  ],
  "abstract": "Recent development in fully convolutional neural network enables efficient end-to-end learning of semantic segmentation. Traditionally, the convolutional classifiers are taught to learn the representative semantic features of labeled semantic objects. In this work, we propose a reverse attention network (RAN) architecture that trains the network to capture the opposite concept (i.e., what are not associated with a target class) as well. The RAN is a three-branch network that performs the direct, reverse and reverse-attention learning processes simultaneously. Extensive experiments are conducted to show the effectiveness of the RAN in semantic segmentation. Being built upon the DeepLabv2-LargeFOV, the RAN achieves the state-of-the-art mIoU score (48.1%) for the challenging PASCAL-Context dataset. Significant performance improvements are also observed for the PASCAL-VOC, Person-Part, NYUDv2 and ADE20K datasets.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2017-07-20T09:45:08.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "semantic segmentation",
      "reverse attention",
      "enables efficient end-to-end learning",
      "convolutional neural network enables efficient",
      "neural network enables efficient end-to-end"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}