# Adversarial Style Augmentation for Domain Generalization

arXiv: https://arxiv.org/abs/2301.12643 · HTML: https://mlsanity.com/paper/2301.12643/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 50 references that are in the map.
- First posted on arXiv 30 Jan 2023.

## Builds on (most cited first, 30 of 41)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Learning to Generalize: Meta-Learning for Domain Generalization](https://mlsanity.com/paper/1710.03463/) (2017)
- [Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking](https://mlsanity.com/paper/1609.01775/) (2016)
- [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)
- [Domain Generalization by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1903.06864/) (2019)
- [A Learned Representation For Artistic Style](https://mlsanity.com/paper/1610.07629/) (2016)
- [Unified Deep Supervised Domain Adaptation and Generalization](https://mlsanity.com/paper/1709.10190/) (2017)
- [Learning to Generate Novel Domains for Domain Generalization](https://mlsanity.com/paper/2007.03304/) (2020)
- [Omni-Scale Feature Learning for Person Re-Identification](https://mlsanity.com/paper/1905.00953/) (2019)
- [A Fourier-based Framework for Domain Generalization](https://mlsanity.com/paper/2105.11120/) (2021)
- [Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro](https://mlsanity.com/paper/1701.07717/) (2017)
- [DropBlock: A regularization method for convolutional networks](https://mlsanity.com/paper/1810.12890/) (2018)
- [Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Data](https://mlsanity.com/paper/1909.00889/) (2019)
- [DLOW: Domain Flow for Adaptation and Generalization](https://mlsanity.com/paper/1812.05418/) (2018)
- [Learning to Diversify for Single Domain Generalization](https://mlsanity.com/paper/2108.11726/) (2021)
- [Domain Adaptive Ensemble Learning](https://mlsanity.com/paper/2003.07325/) (2020)

## Built on by (most cited first, 16 of 16)

- [Enhance Vision-Language Alignment with Noise](https://mlsanity.com/paper/2412.10817/) (2024)
- [Any-to-Any Style Transfer: Making Picasso and Da Vinci Collaborate](https://mlsanity.com/paper/2304.09728/) (2023)
- [AdvST: Revisiting Data Augmentations for Single Domain Generalization](https://mlsanity.com/paper/2312.12720/) (2023)
- [Towards Combating Frequency Simplicity-biased Learning for Domain Generalization](https://mlsanity.com/paper/2410.16146/) (2024)
- [A Novel Cross-Perturbation for Single Domain Generalization](https://mlsanity.com/paper/2308.00918/) (2023)
- [Transitive Vision-Language Prompt Learning for Domain Generalization](https://mlsanity.com/paper/2404.18758/) (2024)
- [Causality-inspired Latent Feature Augmentation for Single Domain Generalization](https://mlsanity.com/paper/2406.05980/) (2024)
- [Domain Agnostic Conditional Invariant Predictions for Domain Generalization](https://mlsanity.com/paper/2406.05616/) (2024)
- [OSSA: Unsupervised One-Shot Style Adaptation](https://mlsanity.com/paper/2410.00900/) (2024)
- [Boundless Across Domains: A New Paradigm of Adaptive Feature and Cross-Attention for Domain Generalization in Medical Image Segmentation](https://mlsanity.com/paper/2411.14883/) (2024)
- [Single Domain Generalization with Model-aware Parametric Batch-wise Mixup](https://mlsanity.com/paper/2502.16064/) (2025)
- [Single Domain Generalization with Adversarial Memory](https://mlsanity.com/paper/2503.06288/) (2025)
- [Target-Oriented Single Domain Generalization](https://mlsanity.com/paper/2509.00351/) (2025)
- [PSScreen V2: Partially Supervised Multiple Retinal Disease Screening](https://mlsanity.com/paper/2510.22589/) (2025)
- [Adversarial Batch Representation Augmentation for Batch Correction in High-Content Cellular Screening](https://mlsanity.com/paper/2603.05622/) (2026)
- [Bi-Level Optimization for Single Domain Generalization](https://mlsanity.com/paper/2604.06349/) (2026)

## Abstract (arXiv)

It is well-known that the performance of well-trained deep neural networks may degrade significantly when they are applied to data with even slightly shifted distributions. Recent studies have shown that introducing certain perturbation on feature statistics (eg, mean and standard deviation) during training can enhance the cross-domain generalization ability. Existing methods typically conduct such perturbation by utilizing the feature statistics within a mini-batch, limiting their representation capability. Inspired by the domain generalization objective, we introduce a novel Adversarial Style Augmentation (ASA) method, which explores broader style spaces by generating more effective statistics perturbation via adversarial training. Specifically, we first search for the most sensitive direction and intensity for statistics perturbation by maximizing the task loss. By updating the model against the adversarial statistics perturbation during training, we allow the model to explore the worst-case domain and hence improve its generalization performance. To facilitate the application of ASA, we design a simple yet effective module, namely AdvStyle, which instantiates the ASA method in a plug-and-play manner. We justify the efficacy of AdvStyle on tasks of cross-domain classification and instance retrieval. It achieves higher mean accuracy and lower performance fluctuation. Especially, our method significantly outperforms its competitors on the PACS dataset under the single source generalization setting, eg, boosting the classification accuracy from 61.2% to 67.1% with a ResNet50 backbone. Our code will be available at urlhttps://github.com/YBZh/AdvStyle.