Language-aware domain generalization network for cross-scene hyperspectral image classification

• 论文名称: Language-aware domain generalization network for cross-scene hyperspectral image classification
• 模型架构: VLM
• Visual Encoder: CNN
• Text Encoder: Transformer
• Model Details: Vision Encoder：deep residual 3D CNN networkText Encoder：Transformer Architecture
• Task: Scene Classification
• Link: https://arxiv.org/pdf/2209.02700
• Code/Project: -
• Survey Inclusion: Vision-Language Models in Remote Sensing: Current Progress and Future Trends
• Published in: IEEE Transactions on Geoscience and Remote Sensing 2023