cs.CVNov 17, 2026

SARVIA: Fast-Adapting the Strong SAR Foundation Models That Are Already in Your MLLMs

Authors: Yuxuan Li, Zichen Tian, Qianru Sun

Organizations: Singapore Management University

Abstract

Synthetic aperture radar (SAR) foundation models provide transferable representations for diverse perception tasks in all-weather Earth observation. However, their development often relies on costly large-scale SAR pretraining, raising the question of whether such extensive domain-specific pretraining is necessary. We find that modern multimodal large language models (MLLMs) already provide visual encoders that can outperform dedicated SAR foundation models as downstream initializations. This motivates a new paradigm: reuse general visual capabilities and devote domain training to brief specialization. We therefore introduce SARVIA, an adaptive post-pretraining method that specializes modern MLLMs using self-supervised visual questions with computable answers. These questions are constructed from unlabeled observations through general image tasks that capture spatial relations and SAR-specific tasks that exploit native measurements and SAR--optical correspondence. A shared answer-prediction objective jointly trains low-rank adapters across visual and language components, with loss-driven task sampling. We then export the adapted visual encoder as a standalone backbone. With 600 adaptation steps and 2 GPU-hours, SARVIA outperforms the compared foundation models on all six SAR detection and segmentation benchmarks. Compared with dedicated SAR pretraining, SARVIA reduces domain-training costs by orders of magnitude while improving visual transfer across architectures and scales. This new paradigm shifts the emphasis from repeated, costly pretraining to a reusable specialization process that can benefit from advances in open MLLMs. Dataset and code: https://github.com/zcablii/SARVIA.

Figures & tables

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Cross-modal learning for SAR target recognition using optical vision foundation models

    Sep 7, 2026Lucas Hirsch, James R. Hopgood, Javid Khan +2Cross-Modal AlignmentCross-Modal Representation Transfer

  2. FUSAR-GPT : A Spatiotemporal Feature-Embedded and Two-Stage Decoupled Visual Language Model for SAR Imagery

    Feb 22, 2026Xiaokun Zhang, Yi Yang, Ziqi Ye +6Vision-Language ModelsRemote Sensing Image Understanding