EUVIMEDEUVIMED entdecken
Crossref

Fusing Learning and Non-Learning: Hybrid CNN-Transformer Cooperative-Competitive Network for Underwater Image Enhancement

Xun Ji, Xu Wang, Li-Ying Hao, Chengtao Cai, Chengsong Dai, Ryan Wen Liu

IEEE Transactions on Broadcasting · 2025-12 · 71 (4) · 1065-1078

DOI: 10.1109/tbc.2025.3611669 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Broadcasting, 2025-12. Verfasst von Xun Ji und 5 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 53 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Liaoning Province, Dalian Outstanding Young Talents Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Underwater image enhancement (UIE) aims to provide high-quality observations of challenging underwater scenarios, which is of great significance for various broadcast technologies. Extensive non-learning-based and learning-based UIE methods have been presented and applied. However, non-learning-based strategies typically struggle to demonstrate superior generalization capabilities, while learning-based strategies generally suffer from potential over- or under-enhancement due to the lack of sufficient prior knowledge. To address the challenges above, this paper presents a heuristic cooperative-competitive network, termed Co2Net. Specifically, our Co2Net integrates non-learning mechanisms into the deep learning framework to achieve information fusion from explainable prior knowledge and discernible hierarchical features, thereby facilitating promising and reasonable enhancement of degraded underwater images. Furthermore, our Co2Net adopts a hybrid convolutional neural network (CNN)-Transformer architecture, which comprises successive cooperative-competitive modules (Co2Ms) to achieve adequate extraction, representation, and transmission of both prior knowledge and discernible features. Comprehensive experiments are conducted to demonstrate the superiority and universality of our proposed Co2Net, and sufficient ablation studies are also performed to reveal the effectiveness of each component within our model. The source code is available at https://github.com/jixun-dmu/Co2Net

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Liaoning Province
  • Dalian Outstanding Young Talents Program
  • Excellent Youth Foundation of Hubei Scientific Committee
  • Basic Scientific Research Project of the Educational Department of Liaoning Province
  • Fundamental Research Funds for the Central Universities
  • Open Fund of National Center for International Research of Subsea Engineering Technology and Equipment

Zitieren

APA

Ji, X., Wang, X., Hao, L., Cai, C., Dai, C., & Liu, R. W. (2025). Fusing Learning and Non-Learning: Hybrid CNN-Transformer Cooperative-Competitive Network for Underwater Image Enhancement. IEEE Transactions on Broadcasting, 71(4), 1065-1078. https://doi.org/10.1109/tbc.2025.3611669

Vancouver

Ji X, Wang X, Hao L, Cai C, Dai C, Liu RW. Fusing Learning and Non-Learning: Hybrid CNN-Transformer Cooperative-Competitive Network for Underwater Image Enhancement. IEEE Transactions on Broadcasting. 2025;71(4):1065-1078. doi:10.1109/tbc.2025.3611669

BibTeX
@article{Ji2025,
  author = {Ji, Xun and Wang, Xu and Hao, Li-Ying and Cai, Chengtao and Dai, Chengsong and Liu, Ryan Wen},
  title = {Fusing Learning and Non-Learning: Hybrid CNN-Transformer Cooperative-Competitive Network for Underwater Image Enhancement},
  journal = {IEEE Transactions on Broadcasting},
  year = {2025},
  volume = {71},
  number = {4},
  pages = {1065--1078},
  doi = {10.1109/tbc.2025.3611669}
}
Kostenlos starten →