用低秩微调加速遥感模型洪水分割，省时省力还更准。
Rapid Adaptation of Earth Observation Foundation Models for Segmentation
- 用低秩微调（LoRA）高效适配遥感大模型，仅调整少量参数。
- 相比冻结编码器基线，F1提升6.66点，交并比提高0.11。
- 适合资源受限、需快速响应的灾情监测场景。
本研究探究了低秩微调（LoRA）在洪水分割任务中对地球观测（EO）基础模型微调的有效性。我们假设，这种参数高效的方法能显著加速大规模EO模型在该关键任务上的适应，同时保持高性能。将LoRA应用于一个在多样化卫星影像上预训练的先进EO基础模型，使用精选的洪水事件数据集进行微调。结果表明，基于LoRA的微调（r-256）相比冻结编码器基线，使F1分数提升6.66点，交并比（IoU）提高0.11，同时大幅降低计算成本。值得注意的是，LoRA性能优于全量微调，后者在本实验硬件上不可行。通过在地理上不同的洪水事件上进行分布外（OOD）测试评估泛化能力，结果显示LoRA配置相比基线具有更好的泛化表现。本研究为专用遥感任务中基础模型的高效适配提供了支持，对灾害管理中的快速响应系统具有重要意义。
原文摘要 · Abstract (English)
This study investigates the efficacy of Low-Rank Adaptation (LoRA) in fine-tuning Earth Observation (EO) foundation models for flood segmentation. We hypothesize that LoRA, a parameter-efficient technique, can significantly accelerate the adaptation of large-scale EO models to this critical task while maintaining high performance. We apply LoRA to fine-tune a state-of-the-art EO foundation model pre-trained on diverse satellite imagery, using a curated dataset of flood events. Our results demonstrate that LoRA-based fine-tuning (r-256) improves F1 score by 6.66 points and IoU by 0.11 compared to a frozen encoder baseline, while significantly reducing computational costs. Notably, LoRA outperforms full fine-tuning, which proves computationally infeasible on our hardware. We further assess generalization through out-of-distribution (OOD) testing on a geographically distinct flood event. While LoRA configurations show improved OOD performance over the baseline. This work contributes to research on efficient adaptation of foundation models for specialized EO tasks, with implications for rapid response systems in disaster management. Our findings demonstrate LoRA's potential for enabling faster deployment of accurate flood segmentation models in resource-constrained, time-critical scenarios.
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。