Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning

Understand

Large, pretrained models are commonly finetuned with imagery that is heavily augmented to mimic different conditions and scales, with the resulting models used for various tasks with imagery from a range of spatial scales.

• Such models overlook scale-specific information in the data for scale-dependent domains, such as remote sensing.
• In this paper, we present Scale-MAE, a pretraining method that explicitly learns relationships between data at different, known scales throughout the pretraining process.
• Scale-MAE pretrains a network by masking an input image at a known input scale, where the area of the Earth covered by the image determines the scale of the ViT positional encoding, not the image resolution.