Blind image quality assessment for authentic distortions by intermediary enhancement and iterative training

Song, Tianshu, Li, Leida, Chen, Pengfei, Liu, Hantao ORCID: https://orcid.org/0000-0003-4544-3481 and Qian, Jiansheng 2022. Blind image quality assessment for authentic distortions by intermediary enhancement and iterative training. IEEE Transactions on Circuits and Systems for Video Technology 32 (11) , pp. 7592-7604. 10.1109/TCSVT.2022.3179744

Preview

PDF - Accepted Post-Print Version Download (1MB) | Preview

Abstract

With the boom of deep neural networks, blind image quality assessment (BIQA) has achieved great processes. However, the current BIQA metrics are limited when evaluating low-quality images as compared to medium-quality and high-quality images, which restricts their applications in real world problems. In this paper, we first identify that two challenges caused by distribution shift and long-tailed distribution lead to the compromised performance on low-quality images. Then, we propose an intermediary enhancement-based bilateral network with iterative training strategy for solving these two challenges. Drawing on the experience of transitive transfer learning, the proposed metric adaptively introduces enhanced intermediary images to transfer more information to low-quality images for mitigating the distribution shift. Our metric also adopts an iterative training strategy to deal with the long-tailed distribution. This strategy decouples feature extraction and score regression for better representation learning and regressor training. It not only transfers the knowledge learned from the earlier stage to the latter stage, but also makes the model pay more attention to long-tailed low-quality images. We conduct extensive experiments on five authentically distorted image quality datasets. The results show that our metric significantly improves the evaluating performance on low-quality images and delivers state-of-the-art intra-dataset results. During generalization tests, our metric also achieves the best cross-dataset performance

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics Crime and Security Research Institute (CSURI)
Publisher:	Institute of Electrical and Electronics Engineers
ISSN:	1051-8215
Date of First Compliant Deposit:	9 June 2022
Date of Acceptance:	25 May 2022
Last Modified:	03 Dec 2024 05:15
URI:	https://orca.cardiff.ac.uk/id/eprint/150369

Actions (repository staff only)

Edit Item