{
  "id": "1911.09659",
  "version": "v1",
  "published": "2019-11-21T18:39:01.000Z",
  "updated": "2019-11-21T18:39:01.000Z",
  "title": "AdaFilter: Adaptive Filter Fine-tuning for Deep Transfer Learning",
  "authors": [
    "Yunhui Guo",
    "Yandong Li",
    "Liqiang Wang",
    "Tajana Rosing"
  ],
  "categories": [
    "cs.CV"
  ],
  "abstract": "There is an increasing number of pre-trained deep neural network models. However, it is still unclear how to effectively use these models for a new task. Transfer learning, which aims to transfer knowledge from source tasks to a target task, is an effective solution to this problem. Fine-tuning is a popular transfer learning technique for deep neural networks where a few rounds of training are applied to the parameters of a pre-trained model to adapt them to a new task. Despite its popularity, in this paper, we show that fine-tuning suffers from several drawbacks. We propose an adaptive fine-tuning approach, called AdaFilter, which selects only a part of the convolutional filters in the pre-trained model to optimize on a per-example basis. We use a recurrent gated network to selectively fine-tune convolutional filters based on the activations of the previous layer. We experiment with 7 public image classification datasets and the results show that AdaFilter can reduce the average classification error of the standard fine-tuning by 2.54%.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2019-11-21T18:39:01.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "deep transfer learning",
      "adaptive filter fine-tuning",
      "pre-trained deep neural network models",
      "convolutional filters",
      "public image classification datasets"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}