Skip to main content
Search

# SAR Foundation Models

1 related articles

Subscribe to updates
  1. arXiv

    No SAR pretraining from scratch: SARVIA adapts off-the-shelf multimodal encoders in 600 steps and about 2 GPU-hours

    Synthetic aperture radar (SAR) foundation models usually depend on costly large-scale domain pretraining. SARVIA starts elsewhere: it reuses the visual encoder of an existing multimodal large language model (MLLM), builds self-supervised visual questions with computable answers from unlabeled SAR observations, trains only low-rank adapters for brief specialization, and exports the encoder as a standalone backbone. In the default ViT-L setting, 600 adaptation steps and about 1.92 RTX PRO 6000 GPU-hours lead the compared foundation models on all six SAR detection and segmentation benchmarks.

You’re all caught up