Generalizing to Unseen Domains in Diabetic Retinopathy with Disentangled Representations

TL;DR

This paper introduces a novel framework for diabetic retinopathy classification that disentangles semantic features from domain noise, enhancing model robustness on unseen domains by leveraging augmented representations and semantic alignment.

Contribution

The work proposes a new disentangled representation approach that separates semantic features from domain biases, improving generalization to unseen domains in diabetic retinopathy analysis.

Findings

Effective on multiple benchmarks for unseen domains

Improves robustness of DR classification models

Outperforms existing domain adaptation methods

Abstract

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.