SkyScript A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing

• 论文名称: SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing
• 模型架构: VLM
• Visual Encoder: Transformer
• Text Encoder: Transformer
• Model Details: (CLIP)Vision Encoder: ViT-B/ViT-LText Encoder：Transformer Architecture
• Task: Scene Classification, Image-text Retrieval
• Link: https://arxiv.org/abs/2312.12856
• Code/Project: https://github.com/wangzhecheng/SkyScript
• Published in: AAAI 2024
• 备注: 主要是构建数据集