This paper introduces a Bayesian Meta Pseudo Labeling (BMPL) method for optimizing semi-supervised sea ice classification in marine remote sensing imagery. Addressing the challenge of limited labeled data in marine remote sensing, BMPL optimizes the pseudo-labeling process through a Bayesian inference framework and enhances model generalization via meta-learning strategies. Compared to traditional semi-supervised methods, BMPL demonstrates significant advantages in both theoretical foundations and practical performance. Experiments conducted on a comprehensive dataset including open water, new ice, young ice, and first-year ice showcase the method’s superior performance, particularly in complex mixed-ice and marginal ice zones. BMPL significantly improves the accuracy and efficiency of sea ice classification, providing reliable technical support for marine environment monitoring, marine resource assessment, and polar navigation safety. This research not only advances marine remote sensing technology but also offers a powerful tool for marine ecosystem protection, climate change studies, and sustainable fisheries management, contributing to multiple ocean-related issues.
Bayesian Meta Pseudo Labeling for Sea Ice Classification: Facilitating Marine Disaster Emergency Management
Springer Proceedings Phys.
The Second Global Forum on Space Information for Sustainable Development ; 2024 ; Guangzhou, China September 26, 2024 - September 28, 2024
Proceedings of the Second Global Forum on Space Information for Sustainable Development ; Chapter : 15 ; 219-233
2025-04-28
15 pages
Article/Chapter (Book)
Electronic Resource
English
Sea ice classification , Semi-supervised learning , Meta-learning , Marine remote sensing Physics , Astronomy, Astrophysics and Cosmology , Computer Applications , Geography, general , Optics, Lasers, Photonics, Optical Devices , Geotechnical Engineering & Applied Earth Sciences , Microwaves, RF and Optical Engineering , Physics and Astronomy
British Library Online Contents | 2002
|