The research in image quality assessment (IQA) has a long history, and significant progress has been made by leveraging recent advances in deep neural networks (DNNs). Despite high correlation numbers on existing IQA datasets, DNN-based models may be easily falsified in the group maximum differentiation (gMAD) competition with strong counterexamples being identified. Here we show that gMAD examples can be used to improve blind IQA (BIQA) methods. Specifically, we first pre-train a DNN-based BIQA model using multiple noisy annotators, and fine-tune it on multiple subject-rated databases of synthetically distorted images, resulting in a top-performing baseline model. We then seek pairs of images by comparing the baseline model with a set of full-reference IQA methods in gMAD. The resulting gMAD examples are most likely to reveal the relative weaknesses of the baseline, and suggest potential ways for refinement. We query ground truth quality annotations for the selected images in a well controlled laboratory environment, and further fine-tune the baseline on the combination of human-rated images from gMAD and existing databases. This process may be iterated, enabling active and progressive fine-tuning from gMAD examples for BIQA. We demonstrate the feasibility of our active learning scheme on a large-scale unlabeled image set, and show that the fine-tuned method achieves improved generalizability in gMAD, without destroying performance on previously trained databases.
翻译:图像质量评估(IQA)的研究历史悠久,并且通过利用深层神经网络(DNN)的最近进展取得了显著进展。尽管现有IQA数据集的相关相关数字很高,但基于DNN的模型很容易在集团最大差异(gMAD)竞争中被伪造,并正在确定强有力的反比示例。我们在这里表明,GMAD的例子可以用来改进盲目的IQA(BIQA)方法。具体地说,我们首先利用多个吵闹的告示器对基于DNNN的BIQA模型进行预培训,并在多个按主题评定的合成扭曲图像数据库中对其进行微调,从而形成一个业绩最佳基准模型。我们然后通过将基准模型与一套完全参照的IQA方法方法方法方法进行对比,寻找成对图像的配对。 由此得出的GMAD实例最有可能揭示基线的相对弱点,并提出可能的改进方法。我们先在控制良好的实验室环境中对选定的图像进行实地质量说明,并进一步调整基准,在不精确地将经过合成的、经过合成扭曲的图像组合的基础上,在不断改进的GMAA和现有数据库上展示我们不断改进的、不断改进的系统化的图像。