{
  "id": "2004.05508",
  "version": "v1",
  "published": "2020-04-11T23:36:36.000Z",
  "updated": "2020-04-11T23:36:36.000Z",
  "title": "MetaIQA: Deep Meta-learning for No-Reference Image Quality Assessment",
  "authors": [
    "Hancheng Zhu",
    "Leida Li",
    "Jinjian Wu",
    "Weisheng Dong",
    "Guangming Shi"
  ],
  "categories": [
    "eess.IV",
    "cs.CV"
  ],
  "abstract": "Recently, increasing interest has been drawn in exploiting deep convolutional neural networks (DCNNs) for no-reference image quality assessment (NR-IQA). Despite of the notable success achieved, there is a broad consensus that training DCNNs heavily relies on massive annotated data. Unfortunately, IQA is a typical small sample problem. Therefore, most of the existing DCNN-based IQA metrics operate based on pre-trained networks. However, these pre-trained networks are not designed for IQA task, leading to generalization problem when evaluating different types of distortions. With this motivation, this paper presents a no-reference IQA metric based on deep meta-learning. The underlying idea is to learn the meta-knowledge shared by human when evaluating the quality of images with various distortions, which can then be adapted to unknown distortions easily. Specifically, we first collect a number of NR-IQA tasks for different distortions. Then meta-learning is adopted to learn the prior knowledge shared by diversified distortions. Finally, the quality prior model is fine-tuned on a target NR-IQA task for quickly obtaining the quality model. Extensive experiments demonstrate that the proposed metric outperforms the state-of-the-arts by a large margin. Furthermore, the meta-model learned from synthetic distortions can also be easily generalized to authentic distortions, which is highly desired in real-world applications of IQA metrics.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2020-04-11T23:36:36.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "no-reference image quality assessment",
      "deep meta-learning",
      "deep convolutional neural networks",
      "distortions",
      "dcnn-based iqa metrics operate"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}