Generalizable No-Reference Image Quality Assessment via Deep Meta-Learning
In: IEEE Transactions on Circuits and Systems for Video Technology, Jg. 32 (2022-03-01), S. 1048-1060
Online
unknown
Zugriff:
Recently, researchers have shown great interest in using convolutional neural networks (CNNs) for no-reference image quality assessment (NR-IQA). Due to the lack of big training data, the efforts of existing metrics in optimizing CNN-based NR-IQA models remain limited. Furthermore, the diversity of distortions in images result in the generalization problem of NR-IQA models when trained with known distortions and tested on unseen distortions, which is an easy task for human. Hence, we propose a NR-IQA metric via deep meta-learning, which is highly generalizable in the face of unseen distortions. The fundamental idea is to learn the meta-knowledge shared by human when evaluating the quality of images with diversified distortions. Specifically, we define NR-IQA of different distortions as a series of tasks and propose a task selection strategy to build two task sets, which are characterized by synthetic to synthetic and synthetic to authentic distortions, respectively. Based on these two task sets, an optimization-based meta-learning is proposed to learn the generalized NR-IQA model, which can be directly used to evaluate the quality of images with unseen distortions. Extensive experiments demonstrate that our NR-IQA metric outperforms the state-of-the-arts in terms of both evaluation performance and generalization ability.
Titel: |
Generalizable No-Reference Image Quality Assessment via Deep Meta-Learning
|
---|---|
Autor/in / Beteiligte Person: | Shi, Guangming ; Dong, Weisheng ; Zhu, Hancheng ; Wu, Jinjian ; Li, Leida |
Link: | |
Zeitschrift: | IEEE Transactions on Circuits and Systems for Video Technology, Jg. 32 (2022-03-01), S. 1048-1060 |
Veröffentlichung: | Institute of Electrical and Electronics Engineers (IEEE), 2022 |
Medientyp: | unknown |
ISSN: | 1558-2205 (print) ; 1051-8215 (print) |
DOI: | 10.1109/tcsvt.2021.3073410 |
Schlagwort: |
|
Sonstiges: |
|