KSIQA: A knowledge-sharing model for no-reference image quality assessment

Wang, Huasheng, Liu, Jiang, Tan, Hongchen, Lou, Jianxun, Liu, Xiaochang, Zhou, Wei, Chen, Ying, Whitaker, Roger ORCID: https://orcid.org/0000-0002-8473-1913, Colombo, Walter and Liu, Hantao ORCID: https://orcid.org/0000-0003-4544-3481 2026. KSIQA: A knowledge-sharing model for no-reference image quality assessment. IEEE Transactions on Neural Networks and Learning Systems 10.1109/tnnls.2026.3656757

Full text not available from this repository.

Abstract

No-reference image quality assessment (NR-IQA) aims to quantitatively measure human perception of visual quality without comparing a distorted image to a reference. Despite recent advances, existing NR-IQR approaches often demonstrate insufficient ability to capture perceptual cues in the absence of a reference, limiting their generalisability across diverse and complex real-world image degradations. These limitations hinder their ability to match the reliability of full-reference IQA (FR-IQA) counterparts. A key challenge, therefore, is to enable NR-IQA models to emulate the reference-aware reasoning exhibited by humans and FR-IQA methods. To address this challenge, we propose a novel NR-IQA model based on a knowledge-sharing (KS) strategy to simulate this capability and predict image quality more effectively. Specifically, we designate an FR-IQA model as the teacher and an NR-IQA model as the student. Unlike conventional knowledge distillation (KD), our proposed architecture enables the NR-IQA student and FR-IQA teacher to share a decoder rather than being independent models. Furthermore, the student model contains a Mental Imagery Generation (MIG) module to learn mental imagery as the reference. To fully exploit local and global information, we adopt a vision transformer (ViT) branch and a convolutional neural network branch for feature extraction (FE). Finally, a quality-aware regressor (QAR) combined with deep ordinal regression is constructed to infer the quality score. Experiments show that our proposed NR-IQA model, KSIQA, has class-leading performance against current no-reference (NR) techniques across widespread benchmark datasets.

Item Type:	Article
Date Type:	Published Online
Status:	In Press
Schools:	Schools > Engineering
Publisher:	Institute of Electrical and Electronics Engineers (IEEE)
ISSN:	2162-237X
Date of Acceptance:	12 January 2026
Last Modified:	23 Feb 2026 14:00
URI:	https://orca.cardiff.ac.uk/id/eprint/185127

Actions (repository staff only)

Edit Item