KSIQA: A Knowledge-Sharing Model for No-Reference Image Quality Assessment
IEEE Transactions on Neural Networks and Learning Systems · 2026-08 · 37 (8) · 3943-3955
DOI: 10.1109/tnnls.2026.3656757 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Neural Networks and Learning Systems, 2026-08. Verfasst von Huasheng Wang und 9 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 71 Literaturangaben.
Abstract (Originalsprache)
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.
Zitieren
APA
Wang, H., Liu, J., Tan, H., Lou, J., Liu, X., Zhou, W., Chen, Y., Whitaker, R., Colombo, W., & Liu, H. (2026). KSIQA: A Knowledge-Sharing Model for No-Reference Image Quality Assessment. IEEE Transactions on Neural Networks and Learning Systems, 37(8), 3943-3955. https://doi.org/10.1109/tnnls.2026.3656757
Vancouver
Wang H, Liu J, Tan H, Lou J, Liu X, Zhou W, et al. KSIQA: A Knowledge-Sharing Model for No-Reference Image Quality Assessment. IEEE Transactions on Neural Networks and Learning Systems. 2026;37(8):3943-3955. doi:10.1109/tnnls.2026.3656757
BibTeX
@article{Wang2026,
author = {Wang, Huasheng and Liu, Jiang and Tan, Hongchen and Lou, Jianxun and Liu, Xiaochang and Zhou, Wei and Chen, Ying and Whitaker, Roger and Colombo, Walter and Liu, Hantao},
title = {KSIQA: A Knowledge-Sharing Model for No-Reference Image Quality Assessment},
journal = {IEEE Transactions on Neural Networks and Learning Systems},
year = {2026},
volume = {37},
number = {8},
pages = {3943--3955},
doi = {10.1109/tnnls.2026.3656757}
}
EUVIMED