# Generalizing to Unseen Domains in Diabetic Retinopathy with Disentangled Representations

arXiv: https://arxiv.org/abs/2406.06384 · HTML: https://mlsanity.com/paper/2406.06384/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 37 references that are in the map.
- First posted on arXiv 10 Jun 2024.

## 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)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Domain Generalization with MixStyle](https://mlsanity.com/paper/2104.02008/) (2021)
- [Deep Domain-Adversarial Image Generation for Domain Generalisation](https://mlsanity.com/paper/2003.06054/) (2020)
- [Improving Out-of-Distribution Robustness via Selective Augmentation](https://mlsanity.com/paper/2201.00299/) (2022)
- [Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization](https://mlsanity.com/paper/2109.02934/) (2021)
- [C-Mixup: Improving Generalization in Regression](https://mlsanity.com/paper/2210.05775/) (2022)
- [A Benchmark for Studying Diabetic Retinopathy: Segmentation, Grading, and Transferability](https://mlsanity.com/paper/2008.09772/) (2020)
- [Learn to Segment Retinal Lesions and Beyond](https://mlsanity.com/paper/1912.11619/) (2019)
- [On Multi-Domain Long-Tailed Recognition, Imbalanced Domain Generalization and Beyond](https://mlsanity.com/paper/2203.09513/) (2022)
- [Towards Generalizable Diabetic Retinopathy Grading in Unseen Domains](https://mlsanity.com/paper/2307.04378/) (2023)
- [HGCLIP: Exploring Vision-Language Models with Graph Representations for Hierarchical Understanding](https://mlsanity.com/paper/2311.14064/) (2023)
- [Learning Robust Representation for Joint Grading of Ophthalmic Diseases via Adaptive Curriculum and Feature Disentanglement](https://mlsanity.com/paper/2207.04183/) (2022)
- [NurViD: A Large Expert-Level Video Database for Nursing Procedure Activity Understanding](https://mlsanity.com/paper/2310.13347/) (2023)
- [LMPT: Prompt Tuning with Class-Specific Embedding Loss for Long-tailed Multi-Label Visual Recognition](https://mlsanity.com/paper/2305.04536/) (2023)
- [GREEN: a Graph REsidual rE-ranking Network for Grading Diabetic Retinopathy](https://mlsanity.com/paper/2007.09968/) (2020)
- [Generalizing Across Domains in Diabetic Retinopathy via Variational Autoencoders](https://mlsanity.com/paper/2309.11301/) (2023)
- [Multi-Domain Long-Tailed Learning by Augmenting Disentangled Representations](https://mlsanity.com/paper/2210.14358/) (2022)

## Built on by (most cited first, 11 of 11)

- [MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models](https://mlsanity.com/paper/2410.13085/) (2024)
- [RULE: Reliable Multimodal RAG for Factuality in Medical Vision Language Models](https://mlsanity.com/paper/2407.05131/) (2024)
- [MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference Optimization](https://mlsanity.com/paper/2412.06141/) (2024)
- [TP-DRSeg: Improving Diabetic Retinopathy Lesion Segmentation with Explicit Text-Prompts Assisted SAM](https://mlsanity.com/paper/2406.15764/) (2024)
- [FunOTTA: On-the-Fly Adaptation on Cross-Domain Fundus Image via Stable Test-time Training](https://mlsanity.com/paper/2407.04396/) (2024)
- [Managing Diabetic Retinopathy with Deep Learning: A Data Centric Overview](https://mlsanity.com/paper/2604.02448/) (2026)
- [Low-Rank Adaptive Structural Priors for Generalizable Diabetic Retinopathy Grading](https://mlsanity.com/paper/2504.19362/) (2025)
- [Disentanglement and Assessment of Shortcuts in Ophthalmological Retinal Imaging Exams](https://mlsanity.com/paper/2507.09640/) (2025)
- [From Retinal Pixels to Patients: Evolution of Deep Learning Research in Diabetic Retinopathy Screening](https://mlsanity.com/paper/2511.11065/) (2025)
- [Human Knowledge Integrated Multi-modal Learning for Single Source Domain Generalization](https://mlsanity.com/paper/2603.12369/) (2026)
- [RED-Sphere: Hyperspherical Residual Edge Debiasing for Cross-Population Fundus Disease Domain Generalization](https://mlsanity.com/paper/2607.10777/) (2026)

## Abstract (arXiv)

Diabetic Retinopathy (DR), induced by diabetes, poses a significant risk of visual impairment. Accurate and effective grading of DR aids in the treatment of this condition. Yet existing models experience notable performance degradation on unseen domains due to domain shifts. Previous methods address this issue by simulating domain style through simple visual transformation and mitigating domain noise via learning robust representations. However, domain shifts encompass more than image styles. They overlook biases caused by implicit factors such as ethnicity, age, and diagnostic criteria. In our work, we propose a novel framework where representations of paired data from different domains are decoupled into semantic features and domain noise. The resulting augmented representation comprises original retinal semantics and domain noise from other domains, aiming to generate enhanced representations aligned with real-world clinical needs, incorporating rich information from diverse domains. Subsequently, to improve the robustness of the decoupled representations, class and domain prototypes are employed to interpolate the disentangled representations while data-aware weights are designed to focus on rare classes and domains. Finally, we devise a robust pixel-level semantic alignment loss to align retinal semantics decoupled from features, maintaining a balance between intra-class diversity and dense class features. Experimental results on multiple benchmarks demonstrate the effectiveness of our method on unseen domains. The code implementations are accessible on https://github.com/richard-peng-xia/DECO.