{
  "id": "1910.07856",
  "version": "v1",
  "published": "2019-10-17T12:30:05.000Z",
  "updated": "2019-10-17T12:30:05.000Z",
  "title": "Effect of Superpixel Aggregation on Explanations in LIME -- A Case Study with Biological Data",
  "authors": [
    "Ludwig Schallner",
    "Johannes Rabold",
    "Oliver Scholz",
    "Ute Schmid"
  ],
  "categories": [
    "cs.LG",
    "stat.ML"
  ],
  "abstract": "End-to-end learning with deep neural networks, such as convolutional neural networks (CNNs), has been demonstrated to be very successful for different tasks of image classification. To make decisions of black-box approaches transparent, different solutions have been proposed. LIME is an approach to explainable AI relying on segmenting images into superpixels based on the Quick-Shift algorithm. In this paper, we present an explorative study of how different superpixel methods, namely Felzenszwalb, SLIC and Compact-Watershed, impact the generated visual explanations. We compare the resulting relevance areas with the image parts marked by a human reference. Results show that image parts selected as relevant strongly vary depending on the applied method. Quick-Shift resulted in the least and Compact-Watershed in the highest correspondence with the reference relevance areas.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2019-10-17T12:30:05.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "case study",
      "superpixel aggregation",
      "biological data",
      "image parts",
      "deep neural networks"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}