PRUE：一种可规模化落地的田块边界分割实用方案
PRUE: A Practical Recipe for Field Boundary Segmentation at Scale
在遥感田块边界分割任务上，系统对比了18个分割模型与地理空间基础模型（GFM），结论是U-Net语义分割骨干配合复合损失与针对性数据增强，在精度与部署指标上优于实例分割和GFM方案，为遥感密集预测的模型选型与鲁棒性训练提供了可复用的基线配方。
原文依据 a U-Net semantic segmentation model outperforms instance-based and GFM alternatives on a suite of performance and deployment metrics
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论大规模田块边界地图对农业监测任务至关重要。现有的基于卫星影像的田块制图深度学习方法对光照、空间尺度以及地理位置变化较为敏感。我们利用 Fields of The World（FTW）基准，首次对分割模型与地理空间基础模型（GFM）在全球田块边界勾绘任务上开展了系统性评估。我们在统一的实验设置下评估了18个模型，结果表明，U-Net 语义分割模型在一系列性能与部署指标上优于基于实例的方法和 GFM 方案。我们提出了一种新的分割方法，将 U-Net 骨干、复合损失函数与针对性数据增强相结合，以提升真实场景下的性能与鲁棒性。我们的模型在 FTW 上取得 76% 的 IoU 和 47% 的 object-F1，相较此前基线分别提升 6% 和 9%。我们的方法在模型设计、训练与推理各环节提供了一个可靠、可扩展且可复现的田块边界勾绘实用框架。我们公开发布了全部模型以及覆盖五个国家的模型导出的田块边界数据集。
英文原文摘要 1171 字符
Large-scale maps of field boundaries are essential for agricultural monitoring tasks. Existing deep learning approaches for satellite-based field mapping are sensitive to illumination, spatial scale, and changes in geographic location. We conduct the first systematic evaluation of segmentation and geospatial foundation models (GFMs) for global field boundary delineation using the Fields of The World (FTW) benchmark. We evaluate 18 models under unified experimental settings, showing that a U-Net semantic segmentation model outperforms instance-based and GFM alternatives on a suite of performance and deployment metrics. We propose a new segmentation approach that combines a U-Net backbone, composite loss functions, and targeted data augmentations to enhance performance and robustness under real-world conditions. Our model achieves a 76% IoU and 47% object-F1 on FTW, an increase of 6% and 9% over the previous baseline. Our approach provides a practical framework for reliable, scalable, and reproducible field boundary delineation across model design, training, and inference. We release all models and model-derived field boundary datasets for five countries.