{
  "id": "2401.07586",
  "version": "v1",
  "published": "2024-01-15T10:46:01.000Z",
  "updated": "2024-01-15T10:46:01.000Z",
  "title": "Curriculum for Crowd Counting -- Is it Worthy?",
  "authors": [
    "Muhammad Asif Khan",
    "Hamid Menouar",
    "Ridha Hamila"
  ],
  "comment": "Accepted version of the paper in 19th International Conference on Computer Vision Theory and Applications (VISAPP), Rome, Italy, 27-19 February 2024",
  "categories": [
    "cs.CV",
    "cs.AI"
  ],
  "abstract": "Recent advances in deep learning techniques have achieved remarkable performance in several computer vision problems. A notably intuitive technique called Curriculum Learning (CL) has been introduced recently for training deep learning models. Surprisingly, curriculum learning achieves significantly improved results in some tasks but marginal or no improvement in others. Hence, there is still a debate about its adoption as a standard method to train supervised learning models. In this work, we investigate the impact of curriculum learning in crowd counting using the density estimation method. We performed detailed investigations by conducting 112 experiments using six different CL settings using eight different crowd models. Our experiments show that curriculum learning improves the model learning performance and shortens the convergence time.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2024-01-15T10:46:01.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "crowd counting",
      "computer vision problems",
      "density estimation method",
      "training deep learning models",
      "deep learning techniques"
    ],
    "tags": [
      "conference paper"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}