A single JEPA-based model with scale-adaptive encoders is pre-trained on five heterogeneous Earth observation datasets and reaches state-of-the-art results across nine downstream tasks.
Self-supervised learning from images with a joint-embedding predictive architecture
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
AnySat: One Earth Observation Model for Many Resolutions, Scales, and Modalities
A single JEPA-based model with scale-adaptive encoders is pre-trained on five heterogeneous Earth observation datasets and reaches state-of-the-art results across nine downstream tasks.