Integrating Global Context Contrast and Local Sensitivity for Blind Image Quality Assessment

Xudong Li, Runze Hu, Jingyuan Zheng, Yan Zhang, Shengchuan Zhang, Xiawu Zheng, Ke Li, Yunhang Shen, Yutao Liu, Pingyang Dai, Rongrong Ji
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27920-27941, 2024.

Abstract

Blind Image Quality Assessment (BIQA) mirrors subjective made by human observers. Generally, humans favor comparing relative qualities over predicting absolute qualities directly. However, current BIQA models focus on mining the "local" context, i.e., the relationship between information among individual images and the absolute quality of the image, ignoring the "global" context of the relative quality contrast among different images in the training data. In this paper, we present the Perceptual Context and Sensitivity BIQA (CSIQA), a novel contrastive learning paradigm that seamlessly integrates "global” and "local” perspectives into the BIQA. Specifically, the CSIQA comprises two primary components: 1) A Quality Context Contrastive Learning module, which is equipped with different contrastive learning strategies to effectively capture potential quality correlations in the global context of the dataset. 2) A Quality-aware Mask Attention Module, which employs the random mask to ensure the consistency with visual local sensitivity, thereby improving the model’s perception of local distortions. Extensive experiments on eight standard BIQA datasets demonstrate the superior performance to the state-of-the-art BIQA methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-li24ac, title = {Integrating Global Context Contrast and Local Sensitivity for Blind Image Quality Assessment}, author = {Li, Xudong and Hu, Runze and Zheng, Jingyuan and Zhang, Yan and Zhang, Shengchuan and Zheng, Xiawu and Li, Ke and Shen, Yunhang and Liu, Yutao and Dai, Pingyang and Ji, Rongrong}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {27920--27941}, 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/li24ac/li24ac.pdf}, url = {https://proceedings.mlr.press/v235/li24ac.html}, abstract = {Blind Image Quality Assessment (BIQA) mirrors subjective made by human observers. Generally, humans favor comparing relative qualities over predicting absolute qualities directly. However, current BIQA models focus on mining the "local" context, i.e., the relationship between information among individual images and the absolute quality of the image, ignoring the "global" context of the relative quality contrast among different images in the training data. In this paper, we present the Perceptual Context and Sensitivity BIQA (CSIQA), a novel contrastive learning paradigm that seamlessly integrates "global” and "local” perspectives into the BIQA. Specifically, the CSIQA comprises two primary components: 1) A Quality Context Contrastive Learning module, which is equipped with different contrastive learning strategies to effectively capture potential quality correlations in the global context of the dataset. 2) A Quality-aware Mask Attention Module, which employs the random mask to ensure the consistency with visual local sensitivity, thereby improving the model’s perception of local distortions. Extensive experiments on eight standard BIQA datasets demonstrate the superior performance to the state-of-the-art BIQA methods.} }
Endnote
%0 Conference Paper %T Integrating Global Context Contrast and Local Sensitivity for Blind Image Quality Assessment %A Xudong Li %A Runze Hu %A Jingyuan Zheng %A Yan Zhang %A Shengchuan Zhang %A Xiawu Zheng %A Ke Li %A Yunhang Shen %A Yutao Liu %A Pingyang Dai %A Rongrong Ji %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-li24ac %I PMLR %P 27920--27941 %U https://proceedings.mlr.press/v235/li24ac.html %V 235 %X Blind Image Quality Assessment (BIQA) mirrors subjective made by human observers. Generally, humans favor comparing relative qualities over predicting absolute qualities directly. However, current BIQA models focus on mining the "local" context, i.e., the relationship between information among individual images and the absolute quality of the image, ignoring the "global" context of the relative quality contrast among different images in the training data. In this paper, we present the Perceptual Context and Sensitivity BIQA (CSIQA), a novel contrastive learning paradigm that seamlessly integrates "global” and "local” perspectives into the BIQA. Specifically, the CSIQA comprises two primary components: 1) A Quality Context Contrastive Learning module, which is equipped with different contrastive learning strategies to effectively capture potential quality correlations in the global context of the dataset. 2) A Quality-aware Mask Attention Module, which employs the random mask to ensure the consistency with visual local sensitivity, thereby improving the model’s perception of local distortions. Extensive experiments on eight standard BIQA datasets demonstrate the superior performance to the state-of-the-art BIQA methods.
APA
Li, X., Hu, R., Zheng, J., Zhang, Y., Zhang, S., Zheng, X., Li, K., Shen, Y., Liu, Y., Dai, P. & Ji, R.. (2024). Integrating Global Context Contrast and Local Sensitivity for Blind Image Quality Assessment. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:27920-27941 Available from https://proceedings.mlr.press/v235/li24ac.html.

Related Material