# On the Status of Foundation Models for SAR Imagery

arXiv: https://arxiv.org/abs/2509.21722 · HTML: https://mlsanity.com/paper/2509.21722/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 41 references that are in the map.
- First posted on arXiv 26 Sep 2025.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (2023)
- [Perception Encoder: The best visual embeddings are not at the output of the network](https://mlsanity.com/paper/2504.13181/) (2025)
- [A Cookbook of Self-Supervised Learning](https://mlsanity.com/paper/2304.12210/) (2023)
- [A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends](https://mlsanity.com/paper/2301.05712/) (2023)
- [Learning by Transduction](https://mlsanity.com/paper/1301.7375/) (2013)
- [Very high resolution canopy height maps from RGB imagery using self-supervised vision transformer and convolutional decoder trained on Aerial Lidar](https://mlsanity.com/paper/2304.07213/) (2023)
- [Surgical-DINO: Adapter Learning of Foundation Models for Depth Estimation in Endoscopic Surgery](https://mlsanity.com/paper/2401.06013/) (2024)
- [Predicting Gradient is Better: Exploring Self-Supervised Learning for SAR ATR with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2311.15153/) (2023)
- [SARATR-X: Toward Building A Foundation Model for SAR Target Recognition](https://mlsanity.com/paper/2405.09365/) (2024)
- [OpenEarthMap-SAR: A Benchmark Synthetic Aperture Radar Dataset for Global High-Resolution Land Cover Mapping](https://mlsanity.com/paper/2501.10891/) (2025)
- [ATRNet-STAR: A Large Dataset and Benchmark Towards Remote Sensing Object Recognition in the Wild](https://mlsanity.com/paper/2501.13354/) (2025)
- [SingLoRA: Low Rank Adaptation Using a Single Matrix](https://mlsanity.com/paper/2507.05566/) (2025)
- [A Global Model Approach to Robust Few-Shot SAR Automatic Target Recognition](https://mlsanity.com/paper/2303.10800/) (2023)
- [PBVS 2024 Solution: Self-Supervised Learning and Sampling Strategies for SAR Classification in Extreme Long-Tail Distribution](https://mlsanity.com/paper/2412.12565/) (2024)

## Built on by (most cited first, 3 of 3)

- [Prompting Foundation Models for Zero-Shot Ship Instance Segmentation in SAR Imagery](https://mlsanity.com/paper/2604.17920/) (2026)
- [SARATR-X-v2: Scale-Aware Structural Pre-Training for SAR Foundation Models](https://mlsanity.com/paper/2607.23238/) (2026)
- [Cross-modal learning for SAR target recognition using optical vision foundation models](https://mlsanity.com/paper/2609.07753/) (2026)

## Abstract (arXiv)

In this work we investigate the viability of foundational AI/ML models for Synthetic Aperture Radar (SAR) object recognition tasks. We are inspired by the tremendous progress being made in the wider community, particularly in the natural image domain where frontier labs are training huge models on web-scale datasets with unprecedented computing budgets. It has become clear that these models, often trained with Self-Supervised Learning (SSL), will transform how we develop AI/ML solutions for object recognition tasks - they can be adapted downstream with very limited labeled data, they are more robust to many forms of distribution shift, and their features are highly transferable out-of-the-box. For these reasons and more, we are motivated to apply this technology to the SAR domain. In our experiments we first run tests with today's most powerful visual foundational models, including DINOv2, DINOv3 and PE-Core and observe their shortcomings at extracting semantically-interesting discriminative SAR target features when used off-the-shelf. We then show that Self-Supervised finetuning of publicly available SSL models with SAR data is a viable path forward by training several AFRL-DINOv2s and setting a new state-of-the-art for SAR foundation models, significantly outperforming today's best SAR-domain model SARATR-X. Our experiments further analyze the performance trade-off of using different backbones with different downstream task-adaptation recipes, and we monitor each model's ability to overcome challenges within the downstream environments (e.g., extended operating conditions and low amounts of labeled data). We hope this work will inform and inspire future SAR foundation model builders, because despite our positive results, we still have a long way to go.