Representing satellite images as sets of per-band pixel scalars enriched with sensor metadata lets a single Perceiver-style encoder classify images across unseen resolution, size, and band configurations.
Scale-mae: A scale-aware masked autoencoder for multiscale geospatial representation learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Atomizer: Generalizing to new modalities by breaking satellite images down to a set of scalars
Representing satellite images as sets of per-band pixel scalars enriched with sensor metadata lets a single Perceiver-style encoder classify images across unseen resolution, size, and band configurations.