{
  "id": "2308.09887",
  "version": "v1",
  "published": "2023-08-19T02:44:25.000Z",
  "updated": "2023-08-19T02:44:25.000Z",
  "title": "Calibrating Uncertainty for Semi-Supervised Crowd Counting",
  "authors": [
    "Chen Li",
    "Xiaoling Hu",
    "Shahira Abousamra",
    "Chao Chen"
  ],
  "comment": "Accepted by ICCV'23",
  "categories": [
    "cs.CV",
    "cs.LG"
  ],
  "abstract": "Semi-supervised crowd counting is an important yet challenging task. A popular approach is to iteratively generate pseudo-labels for unlabeled data and add them to the training set. The key is to use uncertainty to select reliable pseudo-labels. In this paper, we propose a novel method to calibrate model uncertainty for crowd counting. Our method takes a supervised uncertainty estimation strategy to train the model through a surrogate function. This ensures the uncertainty is well controlled throughout the training. We propose a matching-based patch-wise surrogate function to better approximate uncertainty for crowd counting tasks. The proposed method pays a sufficient amount of attention to details, while maintaining a proper granularity. Altogether our method is able to generate reliable uncertainty estimation, high quality pseudolabels, and achieve state-of-the-art performance in semisupervised crowd counting.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2023-08-19T02:44:25.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "semi-supervised crowd counting",
      "calibrating uncertainty",
      "surrogate function",
      "calibrate model uncertainty",
      "supervised uncertainty estimation strategy"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}