arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2512.23903cs.CV
收藏

在百亿级数据规模下扩展遥感基础模型:在百亿级数据规模下的领域权衡

Scaling Remote Sensing Foundation Models: Data Domain Tradeoffs at the Peta-Scale

The MITRE Corporation(MITRE公司)

Charith Wickrema, Eliza Mace, Hunter Brown, Heidys Cabrera, Nick Krall, Matthew O'Neill, Shivangi Sarkar, Lowell Weissman, Eric Hughes, Guido Zarrella

AI总结:

研究探讨了在百亿级数据规模下扩展遥感基础模型的挑战与权衡,通过训练更大规模的视觉Transformer主干,揭示了数据受限与模型参数受限之间的关系,并提出了优化数据收集和计算资源的策略。

摘要:

我们探讨人工智能的扩展行为,以建立在高分辨率电光学(EO)数据集上训练基础模型的实用技术,这些数据集的规模远超当前最先进的水平。现代多模态机器学习(ML)应用,如用于图像描述、搜索和推理的生成式人工智能(GenAI)系统,依赖于稳健且领域专用的编码器来处理非文本模态。在自然图像领域,互联网级数据丰富,已建立的扩展定律有助于优化模型容量、训练计算和数据集大小的联合扩展。不幸的是,在高价值领域如遥感(RS)中,这些关系的理解要少得多。使用超过四万亿像素的商业卫星EO数据和MITRE的联邦AI沙盒,我们训练了逐步更大的视觉Transformer(ViT)主干,报告在百亿级规模上观察到的成功和失败模式,并分析了在其他RS模态之间弥合领域差距的含义。我们发现,即使在这一规模下,性能也与数据受限的领域而非模型参数受限的领域一致。这些实用见解旨在指导数据收集策略、计算预算和优化时间表,以促进前沿规模RS基础模型的未来发展。

英文摘要:

We explore the scaling behaviors of artificial intelligence to establish practical techniques for training foundation models on high-resolution electro-optical (EO) datasets that exceed the current state-of-the-art scale by orders of magnitude. Modern multimodal machine learning (ML) applications, such as generative artificial intelligence (GenAI) systems for image captioning, search, and reasoning, depend on robust, domain-specialized encoders for non-text modalities. In natural image domains where internet-scale data is plentiful, well-established scaling laws help optimize the joint scaling of model capacity, training compute, and dataset size. Unfortunately, these relationships are much less well understood in high-value domains like remote sensing (RS). Using over a quadrillion pixels of commercial satellite EO data and MITRE's Federal AI Sandbox, we train progressively larger vision transformer (ViT) backbones, report successes and failure modes observed at peta-scale, and analyze implications for bridging domain gaps across additional RS modalities. We observe that even at this scale, performance is consistent with a data-limited regime rather than a model parameter-limited one. These practical insights are intended to inform data collection strategies, compute budgets, and optimization schedules that advance the future development of frontier scale RS foundation models.

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。

↑