TerraMAE提升高光谱遥感图像的时空特征学习能力
TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders
- 基于光谱反射特性自适应分组通道，捕捉复杂光谱关联
- 重建损失融合空间与光谱质量指标，保留高保真细节
- 在作物识别等三类任务中表现优异，适合地理分析场景
高光谱卫星影像在数百个连续波段中提供亚30米分辨率的地球观测数据，可实现土壤、作物和地表覆盖的细粒度制图。尽管自监督掩码自编码器在RGB和低波段多光谱数据上表现优异，但在200+波段的高光谱图像中难以有效利用复杂的时空谱相关性。我们提出TerraMAE，一种专为高光谱影像设计的编码框架，旨在学习适用于多样地理空间分析的高效时空谱嵌入。TerraMAE采用基于统计反射特性的自适应通道分组策略，以捕捉光谱相似性，并引入增强型重建损失函数，融合空间与光谱质量度量。实验表明，TerraMAE在高质量图像重建中表现出卓越的时空谱信息保持能力。此外，通过在作物识别、土地覆盖分类和土壤质地预测三个关键下游任务中的优异表现，验证了其实际效用与学习表示的质量。
原文摘要 · Abstract (English)
Hyperspectral satellite imagery offers sub-30 m views of Earth in hundreds of contiguous spectral bands, enabling fine-grained mapping of soils, crops, and land cover. While self-supervised Masked Autoencoders excel on RGB and low-band multispectral data, they struggle to exploit the intricate spatial-spectral correlations in 200+ band hyperspectral images. We introduce TerraMAE, a novel HSI encoding framework specifically designed to learn highly representative spatial-spectral embeddings for diverse geospatial analyses. TerraMAE features an adaptive channel grouping strategy, based on statistical reflectance properties to capture spectral similarities, and an enhanced reconstruction loss function that incorporates spatial and spectral quality metrics. We demonstrate TerraMAE's effectiveness through superior spatial-spectral information preservation in high-fidelity image reconstruction. Furthermore, we validate its practical utility and the quality of its learned representations through strong performance on three key downstream geospatial tasks: crop identification, land cover classification, and soil texture prediction.
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。