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

Peibei Cao, Dingquan Li, Kede Ma
Conference on Parsimony and Learning, PMLR 234:529-541, 2024.

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 relative 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 based on blind IQA (BIQA) model predictions and deep content-aware features. Experimental results show that the proposed sampling-worthiness module successfully spots diverse failures of the examined BIQA models, which are indeed worthy samples to be included in next-generation datasets.

Cite this Paper

BibTeX
@InProceedings{pmlr-v234-cao24a, title = {Image Quality Assessment: Integrating Model-centric and Data-centric Approaches}, author = {Cao, Peibei and Li, Dingquan and Ma, Kede}, booktitle = {Conference on Parsimony and Learning}, pages = {529--541}, year = {2024}, editor = {Chi, Yuejie and Dziugaite, Gintare Karolina and Qu, Qing and Wang, Atlas Wang and Zhu, Zhihui}, volume = {234}, series = {Proceedings of Machine Learning Research}, month = {03--06 Jan}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v234/cao24a/cao24a.pdf}, url = {https://proceedings.mlr.press/v234/cao24a.html}, 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 relative 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 based on blind IQA (BIQA) model predictions and deep content-aware features. Experimental results show that the proposed sampling-worthiness module successfully spots diverse failures of the examined BIQA models, which are indeed worthy samples to be included in next-generation datasets.} }
Endnote
%0 Conference Paper %T Image Quality Assessment: Integrating Model-centric and Data-centric Approaches %A Peibei Cao %A Dingquan Li %A Kede Ma %B Conference on Parsimony and Learning %C Proceedings of Machine Learning Research %D 2024 %E Yuejie Chi %E Gintare Karolina Dziugaite %E Qing Qu %E Atlas Wang Wang %E Zhihui Zhu %F pmlr-v234-cao24a %I PMLR %P 529--541 %U https://proceedings.mlr.press/v234/cao24a.html %V 234 %X 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 relative 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 based on blind IQA (BIQA) model predictions and deep content-aware features. Experimental results show that the proposed sampling-worthiness module successfully spots diverse failures of the examined BIQA models, which are indeed worthy samples to be included in next-generation datasets.
APA
Cao, P., Li, D. & Ma, K.. (2024). Image Quality Assessment: Integrating Model-centric and Data-centric Approaches. Conference on Parsimony and Learning, in Proceedings of Machine Learning Research 234:529-541 Available from https://proceedings.mlr.press/v234/cao24a.html.

Related Material