Deep blind image quality assessment based on multiple instance regression
Deep blind image quality assessment based on multiple instance regression
复制标题
DOI：
10.1016/j.neucom.2020.12.009
复制
发表时间：
2020-12
期刊：
影响因子：
6
通讯作者：
Dong Liang;Xinbo Gao;Wen Lu;Jie Li
中科院分区：
文献类型：
--
作者：
Dong Liang;Xinbo Gao;Wen Lu;Jie Li
近年来，基于深度学习，尤其是卷积神经网络（CNN）的图像质量评估（IQA）研究得到了快速发展。建立基于cnn的IQA模型最常用的方法是将图像划分成小块，并进行基于小块的训练。然而，该方法存在一个严重的缺陷，即无法获得每个patch的局部ground-truth。这个缺陷会导致次优结果。为了解决这个问题，我们在多实例回归（MIR）框架下提出了一种新的深度盲IQA算法。具体来说，我们假设每个实例（patch）都有一定的概率是负责袋子标签的袋子（image）的主实例。然后，通过对实例的局部质量分数的加权求和，可以计算出袋子的全局质量分数，其中权重为实例为质数的概率。为了简化训练过程，我们提出了一种类似EM的算法，称为条件EM算法，来训练深度MIR IQA模型。实验结果表明，本文提出的深度MIR IQA算法比传统的深度盲IQA算法性能更好。此外，该算法可以作为一个统一的框架来提高任何基于补丁的深度IQA模型的性能。
In recent years, the research of image quality assessment (IQA) based on deep learning, especially convolutional neural network (CNN), has made rapid development. The most widely used way to build a CNN-based IQA model is to divide image into patches and conduct a patch-based training. However, this method has a critical defect that the local ground-truth for each patch is not available. This defect leads to a sub-optimal result. To address this issue, we propose a novel deep blind IQA algorithm under the multiple instance regression (MIR) framework. Specifically, we assume each instance (patch) has a certain probability to be the prime instance of the bag (image), which is responsible for the bag label. Then the global quality score of the bag can be computed by the weighted summation of the local quality scores of the instances, where the weights are the probabilities of the instances to be the prime one. To simplify the training procedure, we propose an EM-like algorithm, called conditional EM algorithm, to train the deep MIR IQA model. Experimental results show that the proposed deep MIR IQA algorithm performs better than the traditional deep blind IQA algorithm. Moreover, the proposed algorithm can be used as a unified framework to improve the performance of any patch-based deep IQA models.