# RetFiner: A Vision-Language Refinement Scheme for Retinal Foundation Models

arXiv: https://arxiv.org/abs/2506.22149 · HTML: https://mlsanity.com/paper/2506.22149/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 30 references that are in the map.
- First posted on arXiv 27 Jun 2025.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [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)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [EVA: Exploring the Limits of Masked Visual Representation Learning at Scale](https://mlsanity.com/paper/2211.07636/) (2022)
- [Self-Supervised Representation Learning: Introduction, Advances and Challenges](https://mlsanity.com/paper/2110.09327/) (2021)
- [A Foundation Language-Image Model of the Retina (FLAIR): Encoding Expert Knowledge in Text Supervision](https://mlsanity.com/paper/2308.07898/) (2023)
- [Learning by Reconstruction Produces Uninformative Features For Perception](https://mlsanity.com/paper/2402.11337/) (2024)
- [Large-scale and Fine-grained Vision-language Pre-training for Enhanced CT Image Understanding](https://mlsanity.com/paper/2501.14548/) (2025)
- [GAMMA Challenge:Glaucoma grAding from Multi-Modality imAges](https://mlsanity.com/paper/2202.06511/) (2022)
- [OCTID: Optical Coherence Tomography Image Database](https://mlsanity.com/paper/1812.07056/) (2018)
- [Towards Unifying Medical Vision-and-Language Pre-training via Soft Prompts](https://mlsanity.com/paper/2302.08958/) (2023)
- [OCTDL: Optical Coherence Tomography Dataset for Image-Based Deep Learning Methods](https://mlsanity.com/paper/2312.08255/) (2023)
- [Harvard Glaucoma Detection and Progression: A Multimodal Multitask Dataset and Generalization-Reinforced Semi-Supervised Learning](https://mlsanity.com/paper/2308.13411/) (2023)
- [Multi-Scale Convolutional Neural Network for Automated AMD Classification using Retinal OCT Images](https://mlsanity.com/paper/2110.03002/) (2021)
- [UrFound: Towards Universal Retinal Foundation Models via Knowledge-Guided Masked Modeling](https://mlsanity.com/paper/2408.05618/) (2024)

## Abstract (arXiv)

The rise of imaging techniques such as optical coherence tomography (OCT) and advances in deep learning (DL) have enabled clinicians and researchers to streamline retinal disease staging. A popular DL approach is self-supervised learning (SSL), where models learn from vast amounts of unlabeled data, avoiding costly annotation. SSL has allowed the development of foundation models (FMs), large models that can be used for a variety of downstream tasks. However, existing FMs for OCT, trained solely on image data, lack a comprehensive and robust semantic understanding of images, as evidenced by their downstream performance (especially for complex tasks), and thus require supervised fine-tuning (which may be unfeasible) to better adapt to specific applications and populations. To address this, we propose RetFiner, an SSL vision-language refinement scheme that improves the representations of existing FMs and enables their efficient and direct adaptation to specific populations for improved downstream performance. Our method uses a diverse set of training objectives which take advantage of the rich supervisory signal found in textual data. We tested RetFiner on the retinal FMs RETFound, UrFound, and VisionFM, showing significant improvements in linear probing performance on seven highly diverse OCT classification tasks, with an average increase of 5.8, 3.9, and 2.1 percentage points over their baselines, respectively. Our code and model weights are publicly available at https://github.com/ronnief1/RetFiner.