Toward a blind image quality evaluator in the wild by learning beyond human opinion scores

Wang，Zhihua1,2; Tang，Zhi Ri2; Zhang，Jianguo1; Fang，Yuming3

2023-05-01

10.1016/j.patcog.2022.109296

PATTERN RECOGNITION   影响因子和分区

0031-3203

1873-5142

Nowadays, most existing blind image quality assessment (BIQA) models inthewild heavily rely on human ratings, which are extraordinarily labor-expensive to collect. Here, we propose an opinion−free BIQA method that learns from multiple annotators to assess the perceptual quality of images captured in the wild. Specifically, we first synthesize distorted images based on the pristine counterparts. We then randomly assemble a set of image pairs from the synthetic images, and use a group of IQA models to assign pseudo-binary labels for each pair indicating which image has higher quality as the supervisory signal. Based on the newly established pseudo-labeled dataset, we train a deep neural network (DNN)-based BIQA model to rank the perceptual quality, optimized for consistency with the binary rank labels. Since there exists domain shift, e.g., distortion shift and content shift, between the synthetic and in-the-wild images, we leverage two ways to alleviate this issue. First, the simulated distortions should be similar to authentic distortions as much as possible. Second, an unsupervised domain adaptation (UDA) module is further applied to encourage learning domain-invariant features between two domains. Extensive experiments demonstrate the effectiveness of our proposed opinion−free BIQA model, yielding SOTA performance in terms of correlation with human opinion scores, as well as gMAD competition. Codes will be made publicly available upon acceptance.

Blind image quality assessment gMAD competition Opinion-free Pseudo binary label Unsupervised domain adaptation

SCI ; EI

英语

第一 ; 通讯

National Key Research and Development Program of China[2021YFF1200800] ; National Natural Science Foundation of China[62276121]

Computer Science ; Engineering

Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic

WOS:000925885600001

ELSEVIER SCI LTD

20230213377379

Deep neural networks

Ergonomics and Human Factors Engineering:461.4

ENGINEERING

2-s2.0-85145969749

Scopus

1.Department of Computer Science and Engineering,Southern University of Science and Technology,Shenzhen,China
2.Department of Computer Science,City University of Hong Kong,Hong Kong
3.School of Information Management,Jiangxi University of Finance and Economics,Nanchang,China

Wang，Zhihua,Tang，Zhi Ri,Zhang，Jianguo,et al. Toward a blind image quality evaluator in the wild by learning beyond human opinion scores[J]. PATTERN RECOGNITION,2023,137.

Wang，Zhihua,Tang，Zhi Ri,Zhang，Jianguo,&Fang，Yuming.(2023).Toward a blind image quality evaluator in the wild by learning beyond human opinion scores.PATTERN RECOGNITION,137.

Wang，Zhihua,et al."Toward a blind image quality evaluator in the wild by learning beyond human opinion scores".PATTERN RECOGNITION 137(2023).