Image Quality Assessment: Integrating Model-Centric and Data-Centric Approaches

• URL: http://arxiv.org/abs/2207.14769v2
• Date: Fri, 8 Dec 2023 10:36:21 GMT
• Title: Image Quality Assessment: Integrating Model-Centric and Data-Centric Approaches
• Authors: Peibei Cao, Dingquan Li, and Kede Ma
• Abstract summary: Learning-based image quality assessment (IQA) has made remarkable progress in the past decade. Nearly all consider the two key components -- model and data -- in isolation.
• Score: 20.931709027443706
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

Err

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.