提出三种农业时序预训练任务，提升遥感作物监测精度
Time2Agri: Temporal Pretext Tasks for Agricultural Monitoring
- 设计时序差异、频率和未来帧预测三类农业特有预训练任务
- 在印度全国尺度上实现54.2%的田块边界分割准确率
- 适合遥感农业监测与自监督学习研究者参考
自监督学习已成为标签高效学习的重要范式，被广泛应用于遥感基础模型（RSFMs）。当前主流模型如SatMAE、DoFA主要依赖掩码自编码或对比学习。然而这些方法常忽略农业景观特有的自然周期性时序特征。为此，本文提出三种面向农业的新型预训练任务：时序差异预测（TD）、时序频率预测（FP）和未来帧预测（FF）。在SICKLE数据集上的全面评估显示，FF在作物制图任务中达到69.6%的交并比（IoU），FP将产量预测误差降至30.7%平均绝对百分比误差（MAPE），均优于所有基线，TD在多数任务中也表现优异。进一步将FF扩展至印度国家级规模，在FTW India数据集上实现54.2%的田块边界分割准确率，显著优于现有方法。
原文摘要 · Abstract (English)
Self Supervised Learning(SSL) has emerged as a prominent paradigm for label-efficient learning, and has been widely utilized by remote sensing foundation models(RSFMs). Recent RSFMs including SatMAE, DoFA, primarily rely on masked autoencoding(MAE), contrastive learning or some combination of them. However, these pretext tasks often overlook the unique temporal characteristics of agricultural landscape, namely nature's cycle. Motivated by this gap, we propose three novel agriculture-specific pretext tasks, namely Time-Difference Prediction(TD), Temporal Frequency Prediction(FP), and Future-Frame Prediction(FF). Comprehensive evaluation on SICKLE dataset shows FF achieves 69.6% IoU on crop mapping and FP reduces yield prediction error to 30.7% MAPE, outperforming all baselines, and TD remains competitive on most tasks. Further, we also scale FF to the national scale of India, achieving 54.2% IoU outperforming all baselines on field boundary delineation on FTW India dataset.
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。