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.

翻译：由糖尿病引发的糖尿病视网膜病变（DR）存在显著的视力损伤风险。对DR进行准确有效的分级有助于该疾病的治疗。然而现有模型因域偏移而在未知域上出现明显的性能退化。先前方法通过简单的视觉变换模拟域风格，并借助学习鲁棒表征来减轻域噪声，从而应对这一问题。但域偏移不仅包含图像风格，还忽视了种族、年龄、诊断标准等隐含因素造成的偏差。本文提出一种新颖框架，将来自不同域的配对数据表征解耦为语义特征和域噪声。由此生成的增强表征包含原始视网膜语义和其他域的域噪声，旨在生成符合真实临床需求、融合多域丰富信息的增强表征。随后，为提升解耦表征的鲁棒性，我们采用类原型和域原型对解耦表征进行插值，同时设计数据感知权重以关注稀有类别和域。最后，我们设计了一种鲁棒的像素级语义对齐损失，用于对齐从特征中解耦出的视网膜语义，在保持类内多样性与密集类特征之间取得平衡。多个基准实验结果表明，本方法在未知域上具有有效性。代码实现已公开于https://github.com/richard-peng-xia/DECO。