# MaxStyle: Adversarial Style Composition for Robust Medical Image Segmentation

arXiv: https://arxiv.org/abs/2206.01737 · HTML: https://mlsanity.com/paper/2206.01737/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 37 references that are in the map.
- First posted on arXiv 2 Jun 2022.

## Builds on (most cited first, 27 of 27)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1804.04732/) (2018)
- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [The Medical Segmentation Decathlon](https://mlsanity.com/paper/2106.05735/) (2021)
- [Domain Generalization with MixStyle](https://mlsanity.com/paper/2104.02008/) (2021)
- [Generalizing to Unseen Domains via Adversarial Data Augmentation](https://mlsanity.com/paper/1805.12018/) (2018)
- [Self-Challenging Improves Cross-Domain Generalization](https://mlsanity.com/paper/2007.02454/) (2020)
- [Domain Generalization via Model-Agnostic Learning of Semantic Features](https://mlsanity.com/paper/1910.13580/) (2019)
- [Learning to Learn Single Domain Generalization](https://mlsanity.com/paper/2003.13216/) (2020)
- [Adversarial Examples Improve Image Recognition](https://mlsanity.com/paper/1911.09665/) (2019)
- [Causality matters in medical imaging](https://mlsanity.com/paper/1912.08142/) (2019)
- [TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning](https://mlsanity.com/paper/2003.04696/) (2020)
- [Robust and Generalizable Visual Representation Learning via Random Convolutions](https://mlsanity.com/paper/2007.13003/) (2020)
- [Uncertainty Modeling for Out-of-Distribution Generalization](https://mlsanity.com/paper/2202.03958/) (2022)
- [Shape-aware Meta-learning for Generalizing Prostate MRI Segmentation to Unseen Domains](https://mlsanity.com/paper/2007.02035/) (2020)
- [MS-Net: Multi-Site Network for Improving Prostate Segmentation with Heterogeneous MRI Data](https://mlsanity.com/paper/2002.03366/) (2020)
- [Adversarial Examples Are a Natural Consequence of Test Error in Noise](https://mlsanity.com/paper/1901.10513/) (2019)
- [Style Augmentation: Data Augmentation via Style Randomization](https://mlsanity.com/paper/1809.05375/) (2018)
- [Realistic Adversarial Data Augmentation for MR Image Segmentation](https://mlsanity.com/paper/2006.13322/) (2020)
- [Cardiac Segmentation on Late Gadolinium Enhancement MRI: A Benchmark Study from Multi-Sequence Cardiac MR Segmentation Challenge](https://mlsanity.com/paper/2006.12434/) (2020)
- [Structure-Preserving Multi-Domain Stain Color Augmentation using Style-Transfer with Disentangled Representations](https://mlsanity.com/paper/2107.12357/) (2021)
- [Learning domain-agnostic visual representation for computational pathology using medically-irrelevant style transfer augmentation](https://mlsanity.com/paper/2102.01678/) (2021)

## Built on by (most cited first, 27 of 27)

- [Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentation](https://mlsanity.com/paper/2207.04892/) (2022)
- [StyleAdv: Meta Style Adversarial Training for Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2302.09309/) (2023)
- [Domain Generalization for Medical Image Analysis: A Review](https://mlsanity.com/paper/2310.08598/) (2023)
- [Devil is in Channels: Contrastive Single Domain Generalization for Medical Image Segmentation](https://mlsanity.com/paper/2306.05254/) (2023)
- [DeSAM: Decoupled Segment Anything Model for Generalizable Medical Image Segmentation](https://mlsanity.com/paper/2306.00499/) (2023)
- [From Denoising Training to Test-Time Adaptation: Enhancing Domain Generalization for Medical Image Segmentation](https://mlsanity.com/paper/2310.20271/) (2023)
- [Adversarial Style Augmentation for Domain Generalization](https://mlsanity.com/paper/2301.12643/) (2023)
- [Treasure in Distribution: A Domain Randomization based Multi-Source Domain Generalization for 2D Medical Image Segmentation](https://mlsanity.com/paper/2305.19949/) (2023)
- [FoPro-KD: Fourier Prompted Effective Knowledge Distillation for Long-Tailed Medical Image Recognition](https://mlsanity.com/paper/2305.17421/) (2023)
- [A Survey on Domain Generalization for Medical Image Analysis](https://mlsanity.com/paper/2402.05035/) (2024)
- [Domain Generalization with Adversarial Intensity Attack for Medical Image Segmentation](https://mlsanity.com/paper/2304.02720/) (2023)
- [StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization](https://mlsanity.com/paper/2406.00275/) (2024)
- [Navigating Distribution Shifts in Medical Image Analysis: A Survey](https://mlsanity.com/paper/2411.05824/) (2024)
- [Shape-intensity knowledge distillation for robust medical image segmentation](https://mlsanity.com/paper/2409.17503/) (2024)
- [Pay Attention to the Atlas: Atlas-Guided Test-Time Adaptation Method for Robust 3D Medical Image Segmentation](https://mlsanity.com/paper/2307.00676/) (2023)
- [Complex Style Image Transformations for Domain Generalization in Medical Images](https://mlsanity.com/paper/2406.00298/) (2024)
- [M3DA: Benchmark for Unsupervised Domain Adaptation in 3D Medical Image Segmentation](https://mlsanity.com/paper/2502.17029/) (2025)
- [ConStyX: Content Style Augmentation for Generalizable Medical Image Segmentation](https://mlsanity.com/paper/2506.10675/) (2025)
- [Fully Automated SAM for Single-source Domain Generalization in Medical Image Segmentation](https://mlsanity.com/paper/2507.17281/) (2025)
- [Casual Inference via Style Bias Deconfounding for Domain Generalization](https://mlsanity.com/paper/2503.16852/) (2025)
- [Encoding Structural Constraints into Segment Anything Models via Probabilistic Graphical Models](https://mlsanity.com/paper/2509.21750/) (2025)
- [Semantic-aware Random Convolution and Source Matching for Domain Generalization in Medical Image Segmentation](https://mlsanity.com/paper/2512.01510/) (2025)
- [Decoupling Wavelet Sub-bands for Single Source Domain Generalization in Fundus Image Segmentation](https://mlsanity.com/paper/2603.28463/) (2026)
- [FGML-DG: Feynman-Inspired Cognitive Science Paradigm for Cross-Domain Medical Image Segmentation](https://mlsanity.com/paper/2604.10524/) (2026)
- [Frequency Adapter with SAM for Generalized Medical Image Segmentation](https://mlsanity.com/paper/2605.09925/) (2026)
- [Improving PET/CT-Based Whole-Body Lesion Segmentation Using Prediction Uncertainty-Augmented Models](https://mlsanity.com/paper/2606.10115/) (2026)
- [PhaseAT: Fourier Phase Adversarial Training for Medical Image Domain Generalization](https://mlsanity.com/paper/2610.01807/) (2026)

## Abstract (arXiv)

Convolutional neural networks (CNNs) have achieved remarkable segmentation accuracy on benchmark datasets where training and test sets are from the same domain, yet their performance can degrade significantly on unseen domains, which hinders the deployment of CNNs in many clinical scenarios. Most existing works improve model out-of-domain (OOD) robustness by collecting multi-domain datasets for training, which is expensive and may not always be feasible due to privacy and logistical issues. In this work, we focus on improving model robustness using a single-domain dataset only. We propose a novel data augmentation framework called MaxStyle, which maximizes the effectiveness of style augmentation for model OOD performance. It attaches an auxiliary style-augmented image decoder to a segmentation network for robust feature learning and data augmentation. Importantly, MaxStyle augments data with improved image style diversity and hardness, by expanding the style space with noise and searching for the worst-case style composition of latent features via adversarial training. With extensive experiments on multiple public cardiac and prostate MR datasets, we demonstrate that MaxStyle leads to significantly improved out-of-distribution robustness against unseen corruptions as well as common distribution shifts across multiple, different, unseen sites and unknown image sequences under both low- and high-training data settings. The code can be found at https://github.com/cherise215/MaxStyle.