月光石：用于月球遥感的多模态基础模型及基准
Moonstone: A Multimodal Foundation Model and Benchmark for Lunar Remote Sensing
AI总结：
针对月球多模态遥感数据分散且无评估机器学习基准的问题，引入月光石基准。贡献包括构建全球月球预训练数据集，提出MG-MAE模型，创建涵盖多任务的基准，其预训练特征在各任务中表现出色。
摘要：
数十年的轨道任务产生了月球的多模态遥感数据，但数据集分散且无评估月球数据机器学习的基准。我们引入了月光石，首个用于月球遥感的多模态基础模型基准。贡献有：来自五个任务的七个仪器家族的28通道、每度128像素的全球月球预训练数据集；MG-MAE模型；六个下游任务的基准。MG-MAE预训练特征在所有任务中优于从头开始的基线，并大幅超越ImageNet预训练和普通MAE基线。数据和代码可获取。
英文摘要：
Decades of orbital missions have produced multi-modal remote sensing data for the Moon, spanning optical imagery, spectroscopy, thermal emission, radar, gravity, and elemental composition. Yet these datasets remain fragmented across archives, and no benchmark exists for evaluating machine learning on lunar data. We introduce Moonstone, the first multi-modal foundation model benchmark for lunar remote sensing. Our contributions are: (1) a 28-channel, 128 pixels-per-degree (~237 m) global lunar pretraining dataset from seven instrument families across five missions, (2) MG-MAE, a modality-grouped masked autoencoder with per-group convolutional tokenizers, a shared Vision Transformer encoder, attention masking for missing modalities, coverage-adaptive masking for heterogeneous spatial coverage, and spectral continuity regularization for physically plausible reconstructions, and (3) a benchmark of six downstream tasks covering classification, regression, and segmentation. MG-MAE pretrained features outperform scratch baselines on all tasks and surpass both ImageNet-pretrained and vanilla MAE baselines by large margins. Data and code are available at https://huggingface.co/datasets/ayushprd/Moonstone and https://github.com/ayushprd/Moonstone .
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
