# Beyond Natural-Image Foundation Models: Benchmarking Satellite Pretraining for Ophthalmic Image Analysis

arXiv: https://arxiv.org/abs/2608.15195 · HTML: https://mlsanity.com/paper/2608.15195/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 37 references that are in the map.
- First posted on arXiv 15 Aug 2026.

## Builds on (most cited first, 15 of 15)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (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)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [OCTA-500: A Retinal Dataset for Optical Coherence Tomography Angiography Study](https://mlsanity.com/paper/2012.07261/) (2020)
- [A Benchmark of Ocular Disease Intelligent Recognition: One Shot for Multi-disease Detection](https://mlsanity.com/paper/2102.07978/) (2021)
- [MedDINOv3: How to adapt vision foundation models for medical image segmentation?](https://mlsanity.com/paper/2509.02379/) (2025)
- [Dino U-Net: Exploiting High-Fidelity Dense Features from Foundation Models for Medical Image Segmentation](https://mlsanity.com/paper/2508.20909/) (2025)
- [Training a high-performance retinal foundation model with half-the-data and 400 times less compute](https://mlsanity.com/paper/2405.00117/) (2024)
- [Foundation Models in Medical Imaging: A Review and Outlook](https://mlsanity.com/paper/2506.09095/) (2025)
- [MIRAGE: Multimodal foundation model and benchmark for comprehensive retinal OCT image analysis](https://mlsanity.com/paper/2506.08900/) (2025)
- [Generalist versus Specialist Vision Foundation Models for Ocular Disease and Oculomics](https://mlsanity.com/paper/2509.03421/) (2025)
- [NeuroSeg Meets DINOv3: Transferring 2D Self-Supervised Visual Priors to 3D Neuron Segmentation via DINOv3 Initialization](https://mlsanity.com/paper/2603.23104/) (2026)

## Abstract (arXiv)

Vision Foundation Models (VFMs) have emerged as a promising approach in medical imaging, producing broadly applicable systems that can be efficiently adapted across diverse imaging modalities, anatomical regions, and clinical tasks. However, VFMs require extensive training data, and their progress in medical image analysis is constrained by limited data availability, privacy concerns, and high development costs. To alleviate these constraints, medical VFMs (MedVFMs) are often built upon weights from generalist models pretrained on vast amounts of publicly available natural images, introducing a substantial distribution shift for medical task adaptation. To address this, we propose satellite imagery as a novel pretraining domain for MedVFM development and benchmarking, motivated by its closer visual alignment with medical data and its freedom from the privacy constraints that limit medical datasets. Across multiple ophthalmic imaging modalities, we compare DINOv3-SAT493m pretrained on 493 million satellite images against DINOv3-LVD1689m pretrained on 1.7 billion natural images, together with two medical specialist baselines: DINOv3-RETFound and MAE-RETFound. Our experiments show that satellite imagery is a stronger pretraining source than natural images for ophthalmic tasks, particularly on en face vascular-rich modalities. On several tasks, satellite pretraining matches or exceeds the medical specialists on high-resolution en face inputs, despite using no medical data.