{
  "id": "2302.01328",
  "version": "v1",
  "published": "2023-02-02T18:58:05.000Z",
  "updated": "2023-02-02T18:58:05.000Z",
  "title": "$IC^3$: Image Captioning by Committee Consensus",
  "authors": [
    "David M. Chan",
    "Austin Myers",
    "Sudheendra Vijayanarasimhan",
    "David A. Ross",
    "John Canny"
  ],
  "categories": [
    "cs.CV",
    "cs.AI",
    "cs.CL",
    "cs.LG"
  ],
  "abstract": "If you ask a human to describe an image, they might do so in a thousand different ways. Traditionally, image captioning models are trained to approximate the reference distribution of image captions, however, doing so encourages captions that are viewpoint-impoverished. Such captions often focus on only a subset of the possible details, while ignoring potentially useful information in the scene. In this work, we introduce a simple, yet novel, method: \"Image Captioning by Committee Consensus\" ($IC^3$), designed to generate a single caption that captures high-level details from several viewpoints. Notably, humans rate captions produced by $IC^3$ at least as helpful as baseline SOTA models more than two thirds of the time, and $IC^3$ captions can improve the performance of SOTA automated recall systems by up to 84%, indicating significant material improvements over existing SOTA approaches for visual description. Our code is publicly available at https://github.com/DavidMChan/caption-by-committee",
  "revisions": [
    {
      "version": "v1",
      "updated": "2023-02-02T18:58:05.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "committee consensus",
      "image captioning",
      "indicating significant material improvements",
      "baseline sota models",
      "humans rate captions"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}