论文标题
图像质量评估：以模型为中心和以数据为中心的方法集成
Image Quality Assessment: Integrating Model-Centric and Data-Centric Approaches
论文作者
论文摘要
基于学习的图像质量评估（IQA）在过去十年中取得了显着的进步，但几乎所有人都将两个关键组成部分（模型和数据）隔离。具体而言，以模型为中心的IQA着重于在固定和广泛重复使用的数据集上开发``更好的''客观质量方法，并有过度适应的危险。以数据为中心的IQA涉及进行心理物理实验来构建``更好''人类注销的数据集，不幸的是，该数据集忽略了数据集创建过程中当前的IQA模型。在本文中，我们首先设计了一系列实验，以计算探测模型和数据的这种隔离阻碍IQA的进一步进展。然后，我们描述一个集成了以模型为中心和数据为中心的IQA的计算框架。作为一个具体示例，我们设计了计算模块，以量化候选图像的抽样值。实验结果表明，所提出的值得采样的模块成功地发现了所检查的盲人IQA模型的各种故障，这些模型确实值得在下一代数据集中包含在内。
Learning-based image quality assessment (IQA) has made remarkable progress in the past decade, but nearly all consider the two key components -- model and data -- in isolation. Specifically, model-centric IQA focuses on developing ``better'' objective quality methods on fixed and extensively reused datasets, with a great danger of overfitting. Data-centric IQA involves conducting psychophysical experiments to construct ``better'' human-annotated datasets, which unfortunately ignores current IQA models during dataset creation. In this paper, we first design a series of experiments to probe computationally that such isolation of model and data impedes further progress of IQA. We then describe a computational framework that integrates model-centric and data-centric IQA. As a specific example, we design computational modules to quantify the sampling-worthiness of candidate images. Experimental results show that the proposed sampling-worthiness module successfully spots diverse failures of the examined blind IQA models, which are indeed worthy samples to be included in next-generation datasets.
