用少量样本训练大模型，精准识别小沙岛海岸线。
Utilizing a Geospatial Foundation Model for Coastline Delineation in Small Sandy Islands
- 用5到181张卫星图微调300M/600M参数的遥感大模型
- 仅5张训练图即达F1 0.94、IoU 0.79
- 适合缺乏数据的沿海地区海岸线监测
我们对NASA与IBM联合开发的Prithvi-EO-2.0地理空间基础模型在小沙岛海岸线提取任务上的表现进行了初步评估。构建并标注了来自马尔代夫两座岛屿的225张多光谱卫星图像数据集，并公开发布。对300M和600M参数版本的Prithvi模型，在5至181张图像的训练子集上进行微调。实验表明，即使仅使用5张训练图像，模型仍可实现高精度（F1值0.94，交并比IoU 0.79）。结果证明了Prithvi强大的迁移学习能力，凸显此类模型在数据匮乏地区支持海岸监测的巨大潜力。
原文摘要 · Abstract (English)
We present an initial evaluation of NASA and IBM's Prithvi-EO-2.0 geospatial foundation model on shoreline delineation of small sandy islands using satellite images. We curated and labeled a dataset of 225 multispectral images of two Maldivian islands, which we publicly release, and fine-tuned both the 300M and 600M parameter versions of Prithvi on training subsets ranging from 5 to 181 images. Our experiments show that even with as few as 5 training images, the models achieve high performance (F1 of 0.94, IoU of 0.79). Our results demonstrate the strong transfer learning capability of Prithvi, underscoring the potential of such models to support coastal monitoring in data-poor regions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。