SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery.
Yezhen CongSamar KhannaChenlin MengPatrick LiuErik RoziYutong HeMarshall BurkeDavid B. LobellStefano ErmonPublished in: NeurIPS (2022)
Keyphrases
- satellite imagery
- multispectral
- remote sensing
- satellite images
- land cover
- remote sensing images
- change detection
- remotely sensed
- multi spectral images
- remote sensing data
- multi band
- hyperspectral
- electro optical
- image data
- spatial resolution
- multispectral images
- training set
- high spatial resolution
- high resolution
- image analysis
- remotely sensed images
- image processing
- urban areas
- supervised learning
- semi supervised
- machine learning
- hyperspectral images
- aerial images
- geographic information systems
- spectral characteristics