Hardness-Aware Prototypical Contrastive Learning for Hyperspectral Coastal Wetlands Classification
Sign Up to like & getrecommendations! Published in 2025 at "IEEE Geoscience and Remote Sensing Letters"
DOI: 10.1109/lgrs.2025.3569763
Abstract: Self-supervised contrastive learning performs well in representing hyperspectral data under limited labels. However, the heterogeneity poses challenges in balancing a fixed temperature to prevent model collapse with accurately identifying hard negatives. In this letter, we… read more here.
Keywords: aware prototypical; prototypical contrastive; hyperspectral coastal; contrastive learning ... See more keywords