{
  "id": "2208.03142",
  "version": "v1",
  "published": "2022-08-05T13:07:51.000Z",
  "updated": "2022-08-05T13:07:51.000Z",
  "title": "BoxShrink: From Bounding Boxes to Segmentation Masks",
  "authors": [
    "Michael Gröger",
    "Vadim Borisov",
    "Gjergji Kasneci"
  ],
  "categories": [
    "cs.CV",
    "cs.LG"
  ],
  "abstract": "One of the core challenges facing the medical image computing community is fast and efficient data sample labeling. Obtaining fine-grained labels for segmentation is particularly demanding since it is expensive, time-consuming, and requires sophisticated tools. On the contrary, applying bounding boxes is fast and takes significantly less time than fine-grained labeling, but does not produce detailed results. In response, we propose a novel framework for weakly-supervised tasks with the rapid and robust transformation of bounding boxes into segmentation masks without training any machine learning model, coined BoxShrink. The proposed framework comes in two variants - rapid-BoxShrink for fast label transformations, and robust-BoxShrink for more precise label transformations. An average of four percent improvement in IoU is found across several models when being trained using BoxShrink in a weakly-supervised setting, compared to using only bounding box annotations as inputs on a colonoscopy image data set. We open-sourced the code for the proposed framework and published it online.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2022-08-05T13:07:51.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "bounding box",
      "segmentation masks",
      "colonoscopy image data set",
      "precise label transformations",
      "efficient data sample"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}