# DisMix: Order-Aware Mixup for Medical Imaging via Disentangling Ordinal and Non-Ordinal Features

arXiv: https://arxiv.org/abs/2608.04652 · HTML: https://mlsanity.com/paper/2608.04652/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 36 of its 62 references that are in the map.
- First posted on arXiv 5 Aug 2026.

## Builds on (most cited first, 30 of 36)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets](https://mlsanity.com/paper/1606.03657/) (2016)
- [Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1804.04732/) (2018)
- [Disentangling by Factorising](https://mlsanity.com/paper/1802.05983/) (2018)
- [Closed-Form Factorization of Latent Semantics in GANs](https://mlsanity.com/paper/2007.06600/) (2020)
- [Toward Multimodal Image-to-Image Translation](https://mlsanity.com/paper/1711.11586/) (2017)
- [Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup](https://mlsanity.com/paper/2009.06962/) (2020)
- [Diffusion-based Image Translation using Disentangled Style and Content Representation](https://mlsanity.com/paper/2209.15264/) (2022)
- [Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity](https://mlsanity.com/paper/2102.03065/) (2021)
- [Fader Networks: Manipulating Images by Sliding Attributes](https://mlsanity.com/paper/1706.00409/) (2017)
- [DiffuseMix: Label-Preserving Data Augmentation with Diffusion Models](https://mlsanity.com/paper/2405.14881/) (2024)
- [Rank-N-Contrast: Learning Continuous Representations for Regression](https://mlsanity.com/paper/2210.01189/) (2022)
- [Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression](https://mlsanity.com/paper/2103.13629/) (2021)
- [SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer](https://mlsanity.com/paper/2412.10958/) (2024)
- [Balanced-MixUp for Highly Imbalanced Medical Image Classification](https://mlsanity.com/paper/2109.09850/) (2021)
- [Moving Window Regression: A Novel Approach to Ordinal Regression](https://mlsanity.com/paper/2203.13122/) (2022)
- [GuidedMixup: An Efficient Mixup Strategy Guided by Saliency Maps](https://mlsanity.com/paper/2306.16612/) (2023)
- [RankMixup: Ranking-Based Mixup Training for Network Calibration](https://mlsanity.com/paper/2308.11990/) (2023)
- [Ord2Seq: Regarding Ordinal Regression as Label Sequence Prediction](https://mlsanity.com/paper/2307.09004/) (2023)
- [CROWDLAB: Supervised learning to infer consensus labels and quality scores for data with multiple annotators](https://mlsanity.com/paper/2210.06812/) (2022)
- [Disentangled Representations from Non-Disentangled Models](https://mlsanity.com/paper/2102.06204/) (2021)
- [Tripod: Three Complementary Inductive Biases for Disentangled Representation Learning](https://mlsanity.com/paper/2404.10282/) (2024)
- [Fast Dawid-Skene: A Fast Vote Aggregation Scheme for Sentiment Classification](https://mlsanity.com/paper/1803.02781/) (2018)
- [SUMix: Mixup with Semantic and Uncertain Information](https://mlsanity.com/paper/2407.07805/) (2024)

## Abstract (arXiv)

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.