# MM-Retinal V2: Transfer an Elite Knowledge Spark into Fundus Vision-Language Pretraining

arXiv: https://arxiv.org/abs/2501.15798 · HTML: https://mlsanity.com/paper/2501.15798/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 26 of its 45 references that are in the map.
- First posted on arXiv 27 Jan 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [Publicly Available Clinical BERT Embeddings](https://mlsanity.com/paper/1904.03323/) (2019)
- [BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs](https://mlsanity.com/paper/2303.00915/) (2023)
- [Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks](https://mlsanity.com/paper/2206.08916/) (2022)
- [Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification](https://mlsanity.com/paper/2207.09519/) (2022)
- [Making the Most of Text Semantics to Improve Biomedical Vision--Language Processing](https://mlsanity.com/paper/2204.09817/) (2022)
- [REFUGE Challenge: A Unified Framework for Evaluating Automated Methods for Glaucoma Assessment from Fundus Photographs](https://mlsanity.com/paper/1910.03667/) (2019)
- [Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning](https://mlsanity.com/paper/2104.03135/) (2021)
- [A Foundation Language-Image Model of the Retina (FLAIR): Encoding Expert Knowledge in Text Supervision](https://mlsanity.com/paper/2308.07898/) (2023)
- [Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language Tasks](https://mlsanity.com/paper/2211.09808/) (2022)
- [DeepOpht: Medical Report Generation for Retinal Images via Deep Models and Visual Explanation](https://mlsanity.com/paper/2011.00569/) (2020)
- [Modeling Caption Diversity in Contrastive Vision-Language Pretraining](https://mlsanity.com/paper/2405.00740/) (2024)
- [OCTID: Optical Coherence Tomography Image Database](https://mlsanity.com/paper/1812.07056/) (2018)
- [RET-CLIP: A Retinal Image Foundation Model Pre-trained with Clinical Diagnostic Reports](https://mlsanity.com/paper/2405.14137/) (2024)
- [OCTDL: Optical Coherence Tomography Dataset for Image-Based Deep Learning Methods](https://mlsanity.com/paper/2312.08255/) (2023)
- [VisionFM: a Multi-Modal Multi-Task Vision Foundation Model for Generalist Ophthalmic Artificial Intelligence](https://mlsanity.com/paper/2310.04992/) (2023)
- [MM-Retinal: Knowledge-Enhanced Foundational Pretraining with Fundus Image-Text Expertise](https://mlsanity.com/paper/2405.11793/) (2024)
- [VisionUnite: A Vision-Language Foundation Model for Ophthalmology Enhanced with Clinical Knowledge](https://mlsanity.com/paper/2408.02865/) (2024)
- [EyeCLIP: A visual-language foundation model for multi-modal ophthalmic image analysis](https://mlsanity.com/paper/2409.06644/) (2024)
- [Non-Invasive to Invasive: Enhancing FFA Synthesis from CFP with a Benchmark Dataset and a Novel Network](https://mlsanity.com/paper/2410.14965/) (2024)
- [Pyramid Pixel Context Adaption Network for Medical Image Classification with Supervised Contrastive Learning](https://mlsanity.com/paper/2303.01917/) (2023)
- [VisionCLIP: An Med-AIGC based Ethical Language-Image Foundation Model for Generalizable Retina Image Analysis](https://mlsanity.com/paper/2403.10823/) (2024)

## Built on by (most cited first, 5 of 5)

- [A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers](https://mlsanity.com/paper/2508.21148/) (2025)
- [Bridging the Gap in Ophthalmic AI: MM-Retinal-Reason Dataset and OphthaReason Model toward Dynamic Multimodal Reasoning](https://mlsanity.com/paper/2508.16129/) (2025)
- [Continual Retinal Vision-Language Pre-training upon Incremental Imaging Modalities](https://mlsanity.com/paper/2506.19320/) (2025)
- [A Survey of Multimodal Ophthalmic Diagnostics: From Task-Specific Approaches to Foundational Models](https://mlsanity.com/paper/2508.03734/) (2025)
- [MedKCO: Medical Vision-Language Pretraining via Knowledge-Driven Cognitive Orchestration](https://mlsanity.com/paper/2603.09101/) (2026)

## Abstract (arXiv)

Vision-language pretraining (VLP) has been investigated to generalize across diverse downstream tasks for fundus image analysis. Although recent methods showcase promising achievements, they significantly rely on large-scale private image-text data but pay less attention to the pretraining manner, which limits their further advancements. In this work, we introduce MM-Retinal V2, a high-quality image-text paired dataset comprising CFP, FFA, and OCT image modalities. Then, we propose a novel fundus vision-language pretraining model, namely KeepFIT V2, which is pretrained by integrating knowledge from the elite data spark into categorical public datasets. Specifically, a preliminary textual pretraining is adopted to equip the text encoder with primarily ophthalmic textual knowledge. Moreover, a hybrid image-text knowledge injection module is designed for knowledge transfer, which is essentially based on a combination of global semantic concepts from contrastive learning and local appearance details from generative learning. Extensive experiments across zero-shot, few-shot, and linear probing settings highlight the generalization and transferability of KeepFIT V2, delivering performance competitive to state-of-the-art fundus VLP models trained on large-scale private image-text datasets. Our dataset and model are publicly available via https://github.com/lxirich/MM-Retinal.