A Composition-Aware Pretraining Framework for Geospatial Foundation Models
Experimental evaluation shows that composition-aware pretraining yields substantial gains on region-level understanding tasks requiring semantic similarity judgment, including zero-shot image retrieval and scene classification, while remaining competitive on tasks requiring fine-grained spatial precision, such as segme...
A. Naveen, Abhishek Srinivas, Pranav Moothedath et al.
· 0 citations