{
  "id": "1708.07689",
  "version": "v1",
  "published": "2017-08-25T11:08:38.000Z",
  "updated": "2017-08-25T11:08:38.000Z",
  "title": "Understanding and Comparing Deep Neural Networks for Age and Gender Classification",
  "authors": [
    "Sebastian Lapuschkin",
    "Alexander Binder",
    "Klaus-Robert Müller",
    "Wojciech Samek"
  ],
  "comment": "8 pages, 5 figures, 5 tables. Presented at ICCV 2017 Workshop: 7th IEEE International Workshop on Analysis and Modeling of Faces and Gestures",
  "categories": [
    "stat.ML",
    "cs.AI",
    "cs.CV",
    "cs.IR",
    "cs.LG"
  ],
  "abstract": "Recently, deep neural networks have demonstrated excellent performances in recognizing the age and gender on human face images. However, these models were applied in a black-box manner with no information provided about which facial features are actually used for prediction and how these features depend on image preprocessing, model initialization and architecture choice. We present a study investigating these different effects. In detail, our work compares four popular neural network architectures, studies the effect of pretraining, evaluates the robustness of the considered alignment preprocessings via cross-method test set swapping and intuitively visualizes the model's prediction strategies in given preprocessing conditions using the recent Layer-wise Relevance Propagation (LRP) algorithm. Our evaluations on the challenging Adience benchmark show that suitable parameter initialization leads to a holistic perception of the input, compensating artefactual data representations. With a combination of simple preprocessing steps, we reach state of the art performance in gender recognition.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2017-08-25T11:08:38.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "deep neural networks",
      "gender classification",
      "popular neural network architectures",
      "human face images",
      "models prediction strategies"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 8,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}