{
  "id": "2009.12547",
  "version": "v1",
  "published": "2020-09-26T09:26:29.000Z",
  "updated": "2020-09-26T09:26:29.000Z",
  "title": "Causal Intervention for Weakly-Supervised Semantic Segmentation",
  "authors": [
    "Dong Zhang",
    "Hanwang Zhang",
    "Jinhui Tang",
    "Xiansheng Hua",
    "Qianru Sun"
  ],
  "comment": "Accepted as a NeurIPS 2020 oral paper",
  "categories": [
    "cs.CV"
  ],
  "abstract": "We present a causal inference framework to improve Weakly-Supervised Semantic Segmentation (WSSS). Specifically, we aim to generate better pixel-level pseudo-masks by using only image-level labels -- the most crucial step in WSSS. We attribute the cause of the ambiguous boundaries of pseudo-masks to the confounding context, e.g., the correct image-level classification of \"horse\" and \"person\" may be not only due to the recognition of each instance, but also their co-occurrence context, making the model inspection (e.g., CAM) hard to distinguish between the boundaries. Inspired by this, we propose a structural causal model to analyze the causalities among images, contexts, and class labels. Based on it, we develop a new method: Context Adjustment (CONTA), to remove the confounding bias in image-level classification and thus provide better pseudo-masks as ground-truth for the subsequent segmentation model. On PASCAL VOC 2012 and MS-COCO, we show that CONTA boosts various popular WSSS methods to new state-of-the-arts.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2020-09-26T09:26:29.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "weakly-supervised semantic segmentation",
      "causal intervention",
      "generate better pixel-level pseudo-masks",
      "causal inference framework",
      "popular wsss methods"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}