ConDiSR：面向单域泛化的对比解耦与风格正则化
ConDiSR: Contrastive Disentanglement and Style Regularization for Single Domain Generalization
AI总结：
针对医学图像分类中数据分布偏移且分类标签缺乏密集结构信息的单域泛化难题，提出结合通道对比解耦与重建式风格正则化的ConDiSR方法，在多中心组织病理分类任务上以1%准确率优势超越现有最优水平且性能更稳定。
摘要：
医学数据常存在分布偏移问题，导致采用标准监督学习流程训练的深度学习模型在测试时性能下降。域泛化（DG）领域旨在解决这一挑战，其中单域泛化（SDG）子领域因医学数据常涉及的隐私或后勤相关问题而备受关注。现有基于解耦的SDG方法高度依赖分割掩码中嵌入的结构信息，但分类标签无法提供此类密集信息。本研究提出一种面向医学图像分类的新型SDG方法，该方法利用通道维度的对比解耦机制，并通过基于重建的风格正则化进一步增强，以确保提取出截然不同的风格特征与结构特征表示。我们在多中心组织病理学图像分类这一复杂任务上评估了所提方法，将其与当前最优（SOTA）的SDG基线方法进行对比。结果表明，我们的方法在平均准确率上以1%的幅度超越了SOTA，同时表现出更稳定的性能。本研究凸显了在分类任务场景下探索SDG框架的重要性与挑战性。代码已公开于https://github.com/BioMedIA-MBZUAI/ConDiSR
英文摘要：
Medical data often exhibits distribution shifts, which cause test-time performance degradation for deep learning models trained using standard supervised learning pipelines. This challenge is addressed in the field of Domain Generalization (DG) with the sub-field of Single Domain Generalization (SDG) being specifically interesting due to the privacy- or logistics-related issues often associated with medical data. Existing disentanglement-based SDG methods heavily rely on structural information embedded in segmentation masks, however classification labels do not provide such dense information. This work introduces a novel SDG method aimed at medical image classification that leverages channel-wise contrastive disentanglement. It is further enhanced with reconstruction-based style regularization to ensure extraction of distinct style and structure feature representations. We evaluate our method on the complex task of multicenter histopathology image classification, comparing it against state-of-the-art (SOTA) SDG baselines. Results demonstrate that our method surpasses the SOTA by a margin of 1% in average accuracy while also showing more stable performance. This study highlights the importance and challenges of exploring SDG frameworks in the context of the classification task. The code is publicly available at https://github.com/BioMedIA-MBZUAI/ConDiSR
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
