提出实用方法，大幅提升全球农田边界分割的准确性和鲁棒性
PRUE: A Practical Recipe for Field Boundary Segmentation at Scale
- 用U-Net结合复合损失和数据增强，提升模型在真实条件下的表现
- 在FTW数据集上达到76%交并比和47%对象F1，优于基线6%和9%
- 适合农业监测、遥感分析等需要大规模可靠农田地图的研究者
大规模农田边界地图对农业监测至关重要。现有基于卫星的深度学习方法对光照、空间尺度和地理变化敏感。我们首次使用Fields of The World（FTW）基准，系统评估了18种分割模型与地理空间基础模型（GFMs）在全局农田边界划分中的表现。实验表明，基于U-Net的语义分割模型在性能与部署指标上均优于实例分割和GFM方案。本文提出一种新方法，结合U-Net骨干网络、复合损失函数和针对性数据增强，显著提升实际场景下的性能与鲁棒性。模型在FTW上实现76%交并比（IoU）和47%对象F1，较先前基线分别提升6%和9%。该方法为模型设计、训练与推理提供了可复现的实用框架。我们公开了五个国家的全部模型及生成的农田边界数据集。
原文摘要 · Abstract (English)
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.
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。