Causal-IQA: Towards the Generalization of Image Quality Assessment Based on Causal Inference

Yan Zhong, Xingyu Wu, Li Zhang, Chenxi Yang, Tingting Jiang
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61747-61762, 2024.

Abstract

Due to the high cost of Image Quality Assessment (IQA) datasets, achieving robust generalization remains challenging for prevalent deep learning-based IQA methods. To address this, this paper proposes a novel end-to-end blind IQA method: Causal-IQA. Specifically, we first analyze the causal mechanisms in IQA tasks and construct a causal graph to understand the interplay and confounding effects between distortion types, image contents, and subjective human ratings. Then, through shifting the focus from correlations to causality, Causal-IQA aims to improve the estimation accuracy of image quality scores by mitigating the confounding effects using a causality-based optimization strategy. This optimization strategy is implemented on the sample subsets constructed by a Counterfactual Division process based on the Backdoor Criterion. Extensive experiments illustrate the superiority of Causal-IQA.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-zhong24e, title = {Causal-{IQA}: Towards the Generalization of Image Quality Assessment Based on Causal Inference}, author = {Zhong, Yan and Wu, Xingyu and Zhang, Li and Yang, Chenxi and Jiang, Tingting}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {61747--61762}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/zhong24e/zhong24e.pdf}, url = {https://proceedings.mlr.press/v235/zhong24e.html}, abstract = {Due to the high cost of Image Quality Assessment (IQA) datasets, achieving robust generalization remains challenging for prevalent deep learning-based IQA methods. To address this, this paper proposes a novel end-to-end blind IQA method: Causal-IQA. Specifically, we first analyze the causal mechanisms in IQA tasks and construct a causal graph to understand the interplay and confounding effects between distortion types, image contents, and subjective human ratings. Then, through shifting the focus from correlations to causality, Causal-IQA aims to improve the estimation accuracy of image quality scores by mitigating the confounding effects using a causality-based optimization strategy. This optimization strategy is implemented on the sample subsets constructed by a Counterfactual Division process based on the Backdoor Criterion. Extensive experiments illustrate the superiority of Causal-IQA.} }
Endnote
%0 Conference Paper %T Causal-IQA: Towards the Generalization of Image Quality Assessment Based on Causal Inference %A Yan Zhong %A Xingyu Wu %A Li Zhang %A Chenxi Yang %A Tingting Jiang %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-zhong24e %I PMLR %P 61747--61762 %U https://proceedings.mlr.press/v235/zhong24e.html %V 235 %X Due to the high cost of Image Quality Assessment (IQA) datasets, achieving robust generalization remains challenging for prevalent deep learning-based IQA methods. To address this, this paper proposes a novel end-to-end blind IQA method: Causal-IQA. Specifically, we first analyze the causal mechanisms in IQA tasks and construct a causal graph to understand the interplay and confounding effects between distortion types, image contents, and subjective human ratings. Then, through shifting the focus from correlations to causality, Causal-IQA aims to improve the estimation accuracy of image quality scores by mitigating the confounding effects using a causality-based optimization strategy. This optimization strategy is implemented on the sample subsets constructed by a Counterfactual Division process based on the Backdoor Criterion. Extensive experiments illustrate the superiority of Causal-IQA.
APA
Zhong, Y., Wu, X., Zhang, L., Yang, C. & Jiang, T.. (2024). Causal-IQA: Towards the Generalization of Image Quality Assessment Based on Causal Inference. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:61747-61762 Available from https://proceedings.mlr.press/v235/zhong24e.html.

Related Material