{
  "id": 217300,
  "title": "Anyone tried MetaIQA: Deep Meta-learning for No-Reference Image Quality Assessment?",
  "url": "/competitions/cassava-leaf-disease-classification/discussion/217300",
  "author_name": "Mobassir",
  "post_date": "2021-02-06T08:27:54.697000",
  "votes": 4,
  "comment_count": 0,
  "views": 0,
  "content": "<h1>Abstract</h1>\n<p>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.</p>\n<p><img src=\"https://i.ibb.co/jTJLdjB/ok.png\" alt=\"\"></p>\n<h1>paper : <a href=\"https://arxiv.org/abs/2004.05508\" target=\"_blank\">https://arxiv.org/abs/2004.05508</a></h1>\n<h1>code : <a href=\"https://github.com/zhuhancheng/MetaIQA\" target=\"_blank\">https://github.com/zhuhancheng/MetaIQA</a></h1>",
  "messages": [
    {
      "id": 1188433,
      "postDate": "2021-02-06T08:27:54.697Z",
      "content": "<h1>Abstract</h1>\n<p>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.</p>\n<p><img src=\"https://i.ibb.co/jTJLdjB/ok.png\" alt=\"\"></p>\n<h1>paper : <a href=\"https://arxiv.org/abs/2004.05508\" target=\"_blank\">https://arxiv.org/abs/2004.05508</a></h1>\n<h1>code : <a href=\"https://github.com/zhuhancheng/MetaIQA\" target=\"_blank\">https://github.com/zhuhancheng/MetaIQA</a></h1>",
      "rawMarkdown": "# Abstract \n\nRecently, 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.\n\n![](https://i.ibb.co/jTJLdjB/ok.png)\n\n#paper : https://arxiv.org/abs/2004.05508\n\n#code : https://github.com/zhuhancheng/MetaIQA",
      "votes": 4
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "1188433": "# Abstract \n\nRecently, 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.\n\n![](https://i.ibb.co/jTJLdjB/ok.png)\n\n#paper : https://arxiv.org/abs/2004.05508\n\n#code : https://github.com/zhuhancheng/MetaIQA"
  }
}