提出可跨分辨率的农田边界分割方法，显著提升精度与泛化能力。
Delineate Anything: Resolution-Agnostic Field Boundary Delineation on Satellite Imagery
- 将农田边界识别转为实例分割任务，构建2200万级多分辨率数据集
- 在[email protected]上提升88.5%，在[email protected]:0.95上提升103%
- 支持零样本迁移，适用于不同分辨率和未见地理区域
从卫星影像中精确划分农田边界对土地管理和作物监测至关重要。然而，现有方法受限于数据集规模小、分辨率差异大及环境多样性。本文将该任务重新定义为实例分割，并提出大规模多分辨率数据集FBIS-22M，包含672,909张高分辨率卫星图像块（分辨率0.25米至10米）和22,926,427个独立田块的实例掩码，显著缩小了农业数据集与其他计算机视觉领域之间的差距。我们进一步提出Delineate Anything模型，在新数据集上训练，达到新的基准水平：[email protected]提升88.5%，[email protected]:0.95提升103%，同时推理速度更快，并在不同分辨率和未见过的地理区域表现出强零样本泛化能力。代码、预训练模型及数据集已公开。
原文摘要 · Abstract (English)
The accurate delineation of agricultural field boundaries from satellite imagery is vital for land management and crop monitoring. However, current methods face challenges due to limited dataset sizes, resolution discrepancies, and diverse environmental conditions. We address this by reformulating the task as instance segmentation and introducing the Field Boundary Instance Segmentation - 22M dataset (FBIS-22M), a large-scale, multi-resolution dataset comprising 672,909 high-resolution satellite image patches (ranging from 0.25 m to 10 m) and 22,926,427 instance masks of individual fields, significantly narrowing the gap between agricultural datasets and those in other computer vision domains. We further propose Delineate Anything, an instance segmentation model trained on our new FBIS-22M dataset. Our proposed model sets a new state-of-the-art, achieving a substantial improvement of 88.5% in [email protected] and 103% in [email protected]:0.95 over existing methods, while also demonstrating significantly faster inference and strong zero-shot generalization across diverse image resolutions and unseen geographic regions. Code, pre-trained models, and the FBIS-22M dataset are available at https://lavreniuk.github.io/Delineate-Anything.
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。