Semi-Supervised Blind Quality Assessment with Confidence-quantifiable Pseudo-label Learning for Authentic Images

Yan Zhong, Chenxi Yang, Suyuan Zhao, Tingting Jiang
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78537-78554, 2025.

Abstract

This paper presents CPL-IQA, a novel semi-supervised blind image quality assessment (BIQA) framework for authentic distortion scenarios. To address the challenge of limited labeled data in IQA area, our approach leverages confidence-quantifiable pseudo-label learning to effectively utilize unlabeled authentically distorted images. The framework operates through a preprocessing stage and two training phases: first converting MOS labels to vector labels via entropy minimization, followed by an iterative process that alternates between model training and label optimization. The key innovations of CPL-IQA include a manifold assumption-based label optimization strategy and a confidence learning method for pseudo-labels, which enhance reliability and mitigate outlier effects. Experimental results demonstrate the framework’s superior performance on real-world distorted image datasets, offering a more standardized semi-supervised learning paradigm without requiring additional supervision or network complexity.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-zhong25d, title = {Semi-Supervised Blind Quality Assessment with Confidence-quantifiable Pseudo-label Learning for Authentic Images}, author = {Zhong, Yan and Yang, Chenxi and Zhao, Suyuan and Jiang, Tingting}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {78537--78554}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/zhong25d/zhong25d.pdf}, url = {https://proceedings.mlr.press/v267/zhong25d.html}, abstract = {This paper presents CPL-IQA, a novel semi-supervised blind image quality assessment (BIQA) framework for authentic distortion scenarios. To address the challenge of limited labeled data in IQA area, our approach leverages confidence-quantifiable pseudo-label learning to effectively utilize unlabeled authentically distorted images. The framework operates through a preprocessing stage and two training phases: first converting MOS labels to vector labels via entropy minimization, followed by an iterative process that alternates between model training and label optimization. The key innovations of CPL-IQA include a manifold assumption-based label optimization strategy and a confidence learning method for pseudo-labels, which enhance reliability and mitigate outlier effects. Experimental results demonstrate the framework’s superior performance on real-world distorted image datasets, offering a more standardized semi-supervised learning paradigm without requiring additional supervision or network complexity.} }
Endnote
%0 Conference Paper %T Semi-Supervised Blind Quality Assessment with Confidence-quantifiable Pseudo-label Learning for Authentic Images %A Yan Zhong %A Chenxi Yang %A Suyuan Zhao %A Tingting Jiang %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-zhong25d %I PMLR %P 78537--78554 %U https://proceedings.mlr.press/v267/zhong25d.html %V 267 %X This paper presents CPL-IQA, a novel semi-supervised blind image quality assessment (BIQA) framework for authentic distortion scenarios. To address the challenge of limited labeled data in IQA area, our approach leverages confidence-quantifiable pseudo-label learning to effectively utilize unlabeled authentically distorted images. The framework operates through a preprocessing stage and two training phases: first converting MOS labels to vector labels via entropy minimization, followed by an iterative process that alternates between model training and label optimization. The key innovations of CPL-IQA include a manifold assumption-based label optimization strategy and a confidence learning method for pseudo-labels, which enhance reliability and mitigate outlier effects. Experimental results demonstrate the framework’s superior performance on real-world distorted image datasets, offering a more standardized semi-supervised learning paradigm without requiring additional supervision or network complexity.
APA
Zhong, Y., Yang, C., Zhao, S. & Jiang, T.. (2025). Semi-Supervised Blind Quality Assessment with Confidence-quantifiable Pseudo-label Learning for Authentic Images. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:78537-78554 Available from https://proceedings.mlr.press/v267/zhong25d.html.

Related Material