论文名称: Generative ConvNet Foundation Model With Sparse Modeling and Low-Frequency Reconstruction for Remote Sensing Image Interpretation Link: https://ieeexplore.ieee.org/abstract/document/1037...
论文名称: SwiMDiff: Scene-wide Matching Contrastive Learning with Diffusion Constraint for Remote Sensing Image Link: https://arxiv.org/abs/2401.05093 Published in: Arxiv 2024 Type: Pretrain ...
论文名称: H2RSVLM: Towards Helpful and Honest Remote Sensing Large Vision Language Model 模型架构: MLLM Visual Encoder: Transformer Text Encoder: Transformer Model Details: Vision Encoder：CLIP V...
论文名称: Bridging Remote Sensors with Multisensor Geospatial Foundation Models Link: https://arxiv.org/abs/2404.01260 Published in: CVPR 2024 Type: Other 备注: 跨传感器的掩码方式。每个传感器有独立的embedding提取器...
论文名称: Evaluating Tool-Augmented Agents in Remote Sensing Platforms 模型架构: Agent Link: https://arxiv.org/abs/2405.00709 Code/Project: - Short Summary: 提出了一个新的基准测试GeoLLM-QA，用于评估和理解工具增强型LLMs...
数据集名称: ChatEarthNet 任务: 遥感图像图文对 发布时间: 2024 模态: 图像、文本 数量: 由ChatGPT-3.5生成的163,488对带有标题的图像-文本对和ChatGPT-4V(vision)生成的另外10,000对带有标题的图像-文本对组成 代码源链接: https://github.com/zhu-xlab/ChatEarthNet ...
数据集名称: Earth Parser Dataset 任务: 遥感图像分割 无监督实例分割和语义分割 发布时间: 2024 模态: 图像 数量: 涵盖了七个不同的场景，总面积超过7.7平方公里，包含约9800万个三维点 代码源链接: https://github.com/romainloiseau/EarthParserDataset 论文源链接: http:...
论文名称: Popeye: A Unified Visual-Language Model for Multi-Source Ship Detection from Remote Sensing Imagery 模型架构: MLLM Visual Encoder: Transformer Text Encoder: Transformer Model Details: ...
论文名称: MTP: Advancing Remote Sensing FoundationModel via Multi-Task Pretraining Link: https://arxiv.org/pdf/2403.13430 Published in: Arxiv 2024 Type: Pretrain Code/Project: https://github...
论文名称: SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery Link: https://arxiv.org/pdf/2312.10115 Published in: CVPR 2024 ...