针对医学分级任务，分离严重程度与外观特征，提升数据增强效果
DisMix: Order-Aware Mixup for Medical Imaging via Disentangling Ordinal and Non-Ordinal Features
- 用双码本VQ-VAE分离等级特征和外观特征
- 等级特征插值生成合理中间等级，外观特征随机变化增多样性
- 在四种医学数据集上优于六种基线方法，尤其适合小样本场景
图像混合增强广泛用于数据扩充，但在医学疾病分级等序数分类任务中表现不佳，因传统混合方式将严重程度线索（序数）与外观变化（非序数）混淆，破坏了临床分级的顺序结构。本文提出DisMix，一种面向序数分类的有序感知混合框架。通过双码本VQ-VAE实现序数与非序数特征的解耦，分别独立处理：对序数码本进行插值以生成有意义的中间等级，对非序数码本进行随机变换以引入外观多样性，同时不干扰序数信号。在四个医学影像数据集上，DisMix在六种图像混合基线与六种序数分类器组合中表现最优，并在数据稀缺和临床分级不一致条件下仍具鲁棒性。
原文摘要 · Abstract (English)
Image mixup is a widely adopted data augmentation strategy, yet it is ill-suited for ordinal classification tasks such as medical disease grading, where labels encode a progression of severity. By indiscriminately blending disease-severity cues (ordinal) with appearance-level variation (non-ordinal), standard mixup produces samples that distort the very ordinal structure that underpins clinical severity grading. We introduce DisMix, an order-aware mixup framework for ordinal classification. DisMix disentangles ordinal and non-ordinal features via a dual-codebook VQ-VAE, allowing each subspace to be mixed independently: ordinal codes are interpolated to produce meaningful intermediate ranks, while non-ordinal codes are varied to introduce appearance diversity without corrupting the ordinal signal. Across four medical imaging datasets, DisMix shows the best aggregate performance among six image mixup baselines paired with six ordinal classifiers and remains effective under data scarcity and clinical grading variability.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。