构建了法国2528平方公里高分辨率多模态地表覆盖数据集
FLAIR-HUB: Large-scale Multimodal Dataset for Land Cover and Crop Mapping
- 融合六类遥感数据，含20厘米分辨率影像与时间序列
- 多模态模型最高达78.2%准确率，65.8% mIoU
- 支持监督学习与多模态预训练，适合遥感研究者使用
高分辨率地球观测（EO）数据的普及推动了全球地表覆盖与作物类型监测的发展。然而，数据量大且异构性高，带来处理与标注挑战。为应对这一问题，法国国家地理与森林信息研究所（IGN）推出FLAIR-HUB，目前最大的多传感器地表覆盖数据集，覆盖法国2528平方公里，提供20厘米级高分辨率标注。该数据集整合六类对齐模态：航空影像、哨兵1/2时间序列、SPOT影像、地形数据及历史航拍图像。通过广泛基准测试，评估了多模态融合与深度学习模型（CNN、Transformer）在地表覆盖或作物分类中的表现，并探索了多任务学习。结果表明多模态融合与细粒度分类具有高度复杂性，综合所有模态时取得最佳性能（78.2%准确率，65.8% mIoU）。FLAIR-HUB支持监督学习与多模态预训练，数据与代码已开源：https://ignf.github.io/FLAIR/flairhub。
原文摘要 · Abstract (English)
The growing availability of high-quality Earth Observation (EO) data enables accurate global land cover and crop type monitoring. However, the volume and heterogeneity of these datasets pose major processing and annotation challenges. To address this, the French National Institute of Geographical and Forest Information (IGN) is actively exploring innovative strategies to exploit diverse EO data, which require large annotated datasets. IGN introduces FLAIR-HUB, the largest multi-sensor land cover dataset with very-high-resolution (20 cm) annotations, covering 2528 km2 of France. It combines six aligned modalities: aerial imagery, Sentinel-1/2 time series, SPOT imagery, topographic data, and historical aerial images. Extensive benchmarks evaluate multimodal fusion and deep learning models (CNNs, transformers) for land cover or crop mapping and also explore multi-task learning. Results underscore the complexity of multimodal fusion and fine-grained classification, with best land cover performance (78.2% accuracy, 65.8% mIoU) achieved using nearly all modalities. FLAIR-HUB supports supervised and multimodal pretraining, with data and code available at https://ignf.github.io/FLAIR/flairhub.
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。