{
  "id": "1911.11938",
  "version": "v1",
  "published": "2019-11-27T03:54:15.000Z",
  "updated": "2019-11-27T03:54:15.000Z",
  "title": "Transfer Learning in Visual and Relational Reasoning",
  "authors": [
    "T. S. Jayram",
    "Vincent Marois",
    "Tomasz Kornuta",
    "Vincent Albouy",
    "Emre Sevgen",
    "Ahmet S. Ozcan"
  ],
  "comment": "20 pages",
  "categories": [
    "cs.CV",
    "cs.AI",
    "cs.LG"
  ],
  "abstract": "Transfer learning is becoming the de facto solution for vision and text encoders in the front-end processing of machine learning solutions. Utilizing vast amounts of knowledge in pre-trained models and subsequent fine-tuning allows achieving better performance in domains where labeled data is limited. In this paper, we analyze the efficiency of transfer learning in visual reasoning by introducing a new model (SAMNet) and testing it on two datasets: COG and CLEVR. Our new model achieves state-of-the-art accuracy on COG and shows significantly better generalization capabilities compared to the baseline. We also formalize a taxonomy of transfer learning for visual reasoning around three axes: feature, temporal, and reasoning transfer. Based on extensive experimentation of transfer learning on each of the two datasets, we show the performance of the new model along each axis.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2019-11-27T03:54:15.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "transfer learning",
      "relational reasoning",
      "model achieves state-of-the-art accuracy",
      "significantly better generalization capabilities",
      "machine learning solutions"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 20,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}