{
  "id": "2010.05210",
  "version": "v1",
  "published": "2020-10-11T10:13:21.000Z",
  "updated": "2020-10-11T10:13:21.000Z",
  "title": "Generalized Few-Shot Semantic Segmentation",
  "authors": [
    "Zhuotao Tian",
    "Xin Lai",
    "Li Jiang",
    "Michelle Shu",
    "Hengshuang Zhao",
    "Jiaya Jia"
  ],
  "comment": "8 pages",
  "categories": [
    "cs.CV"
  ],
  "abstract": "Training semantic segmentation models requires a large amount of finely annotated data, making it hard to quickly adapt to novel classes not satisfying this condition. Few-Shot Segmentation (FS-Seg) tackles this problem with many constraints. In this paper, we introduce a new benchmark, called Generalized Few-Shot Semantic Segmentation (GFS-Seg), to analyze the generalization ability of segmentation models to simultaneously recognize novel categories with very few examples as well as base categories with sufficient examples. Previous state-of-the-art FS-Seg methods fall short in GFS-Seg and the performance discrepancy mainly comes from the constrained training setting of FS-Seg. To make GFS-Seg tractable, we set up a GFS-Seg baseline that achieves decent performance without structural change on the original model. Then, as context is the key for boosting performance on semantic segmentation, we propose the Context-Aware Prototype Learning (CAPL) that significantly improves performance by leveraging the contextual information to update class prototypes with aligned features. Extensive experiments on Pascal-VOC and COCO manifest the effectiveness of CAPL, and CAPL also generalizes well to FS-Seg.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2020-10-11T10:13:21.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "generalized few-shot semantic segmentation",
      "state-of-the-art fs-seg methods fall short",
      "segmentation models",
      "update class prototypes",
      "achieves decent performance"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 8,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}