Underwater Ranker: Learn Which Is Better and How to Be Better
Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (1) · 702-709
DOI: 10.1609/aaai.v37i1.25147 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Chunle Guo und 6 weiteren Autor:innen. Die Arbeit wurde bisher 208-mal zitiert (Crossref).
Abstract (Originalsprache)
In this paper, we present a ranking-based underwater image quality assessment (UIQA) method, abbreviated as URanker. The URanker is built on the efficient conv-attentional image Transformer. In terms of underwater images, we specially devise (1) the histogram prior that embeds the color distribution of an underwater image as histogram token to attend global degradation and (2) the dynamic cross-scale correspondence to model local degradation. The final prediction depends on the class tokens from different scales, which comprehensively considers multi-scale dependencies. With the margin ranking loss, our URanker can accurately rank the order of underwater images of the same scene enhanced by different underwater image enhancement (UIE) algorithms according to their visual quality. To achieve that, we also contribute a dataset, URankerSet, containing sufficient results enhanced by different UIE algorithms and the corresponding perceptual rankings, to train our URanker. Apart from the good performance of URanker, we found that a simple U-shape UIE network can obtain promising performance when it is coupled with our pre-trained URanker as additional supervision. In addition, we also propose a normalization tail that can significantly improve the performance of UIE networks. Extensive experiments demonstrate the state-of-the-art performance of our method. The key designs of our method are discussed. Our code and dataset are available at https://li-chongyi.github.io/URanker_files/.
Zitieren
APA
Guo, C., Wu, R., Jin, X., Han, L., Zhang, W., Chai, Z., & Li, C. (2023). Underwater Ranker: Learn Which Is Better and How to Be Better. Proceedings of the AAAI Conference on Artificial Intelligence, 37(1), 702-709. https://doi.org/10.1609/aaai.v37i1.25147
Vancouver
Guo C, Wu R, Jin X, Han L, Zhang W, Chai Z, et al. Underwater Ranker: Learn Which Is Better and How to Be Better. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(1):702-709. doi:10.1609/aaai.v37i1.25147
BibTeX
@article{Guo2023,
author = {Guo, Chunle and Wu, Ruiqi and Jin, Xin and Han, Linghao and Zhang, Weidong and Chai, Zhi and Li, Chongyi},
title = {Underwater Ranker: Learn Which Is Better and How to Be Better},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2023},
volume = {37},
number = {1},
pages = {702--709},
doi = {10.1609/aaai.v37i1.25147}
}
EUVIMED