论文名称: S2MAE: A Spatial-Spectral Pretraining Foundation Model for Spectral Remote Sensing Data Link: https://github.com/Jack-bo1220/Awesome-Remote-Sensing-Foundation-Models/blob/main Publishe...
论文名称: RingMo: A Remote Sensing Foundation Model With Masked Image Modeling Link: https://ieeexplore.ieee.org/abstract/document/9844015 Published in: IEEE Transactions on Geoscience and Remo...
论文名称: LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model 模型架构: MLLM Visual Encoder: Transformer Text Encoder: Transformer Model Details: Vision Encoder...
论文名称: Charting New Territories: Exploring the Geographic and Geospatial Capabilities of Multimodal LLMs 模型架构: Other Link: https://arxiv.org/abs/2311.14656 Code/Project: - Published in: A...
论文名称: Rethinking Transformers Pre-training for Multi-Spectral Satellite Imagery Link: https://arxiv.org/abs/2403.05419 Published in: CVPR 2024 Type: Pretrain 备注: 执行多尺度预训练，并利用基于卷积的上采样块在更高...
论文名称: RemoteCLIP: A Vision Language Foundation Model for Remote Sensing 模型架构: VLM Visual Encoder: CNN, Transformer Text Encoder: Transformer Model Details: (CLIP)Vision Encoder:ResNet-50...
论文名称: One for All: Toward Unified Foundation Models for Earth Vision Link: https://arxiv.org/abs/2401.07527 Published in: Arxiv 2024 Type: Pretrain Code/Project: — 备注: 掩码，在主干前加了不同模态的编码...
论文名称: LeMeViT: Efficient Vision Transformer with Learnable Meta Tokens for Remote Sensing Image Interpretation Published in: IJCAI 2024 Type: Other 备注: 改网络结构，加速
论文名称: EarthGPT: A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domain 模型架构: MLLM Visual Encoder: CNN, Transformer Text Encoder: Transfo...
数据集名称: GeoPile-2 任务: 遥感图像多模态预训练 发布时间: 2024 模态: 图像 数量: 四种模态、约两百万张图像 代码源链接: https://github.com/boranhan/Geospatial_Foundation_Models 论文源链接: http://arxiv.org/abs/2404.01260 详细描述: 整合了四...