对比3种大模型在小麦作物分类中的表现，发现预训练模型效果显著。
Benchmarking foundation models for hyperspectral image classification: Application to cereal crop type mapping
- 用多时相高光谱数据预训练模型，再微调用于作物分类。
- 预训练模型最高准确率达93.5%，远超未预训练模型。
- 模型架构对跨区域泛化能力至关重要，适合遥感应用研究者。
基础模型正在改变地球观测领域，但其在高光谱作物分类中的潜力仍待挖掘。本研究评估了三种基础模型在小麦作物分类中的表现：HyperSigma、DOFA，以及在SpectralEarth数据集上预训练的视觉变换器（Vision Transformer）。这些模型在人工标注的训练区进行微调，并在独立测试区评估，使用总体精度（OA）、平均精度（AA）和F1分数衡量性能。结果表明，HyperSigma的OA为34.5%（±1.8%），DOFA达到62.6%（±3.5%），而SpectralEarth预训练模型取得93.5%（±0.8%）的OA。一个从头训练的紧凑版SpectralEarth模型也达到了91%的精度，凸显模型架构对跨地理区域和传感器平台泛化能力的重要性。该研究为高光谱作物分类的基础模型提供了系统性评估，并指明了未来模型发展的方向。
原文摘要 · Abstract (English)
Foundation models are transforming Earth observation, but their potential for hyperspectral crop mapping remains underexplored. This study benchmarks three foundation models for cereal crop mapping using hyperspectral imagery: HyperSigma, DOFA, and Vision Transformers pre-trained on the SpectralEarth dataset (a large multitemporal hyperspectral archive). Models were fine-tuned on manually labeled data from a training region and evaluated on an independent test region. Performance was measured with overall accuracy (OA), average accuracy (AA), and F1-score. HyperSigma achieved an OA of 34.5% (+/- 1.8%), DOFA reached 62.6% (+/- 3.5%), and the SpectralEarth model achieved an OA of 93.5% (+/- 0.8%). A compact SpectralEarth variant trained from scratch achieved 91%, highlighting the importance of model architecture for strong generalization across geographic regions and sensor platforms. These results provide a systematic evaluation of foundation models for operational hyperspectral crop mapping and outline directions for future model development.
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。