# Improving Diversity with Adversarially Learned Transformations for Domain Generalization

arXiv: https://arxiv.org/abs/2206.07736 · HTML: https://mlsanity.com/paper/2206.07736/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 51 references that are in the map.
- First posted on arXiv 15 Jun 2022.

## Builds on (most cited first, 30 of 38)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [In Search of Lost Domain Generalization](https://mlsanity.com/paper/2007.01434/) (2020)
- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Learning to Generalize: Meta-Learning for Domain Generalization](https://mlsanity.com/paper/1710.03463/) (2017)
- [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)
- [Adversarial Examples: Attacks and Defenses for Deep Learning](https://mlsanity.com/paper/1712.07107/) (2017)
- [Learning to Learn Single Domain Generalization](https://mlsanity.com/paper/2003.13216/) (2020)
- [Learning to Generate Novel Domains for Domain Generalization](https://mlsanity.com/paper/2007.03304/) (2020)
- [Generalisation in humans and deep neural networks](https://mlsanity.com/paper/1808.08750/) (2018)
- [Stochastic Activation Pruning for Robust Adversarial Defense](https://mlsanity.com/paper/1803.01442/) (2018)
- [Robust and Generalizable Visual Representation Learning via Random Convolutions](https://mlsanity.com/paper/2007.13003/) (2020)
- [Learning Data Augmentation Strategies for Object Detection](https://mlsanity.com/paper/1906.11172/) (2019)
- [MNIST-C: A Robustness Benchmark for Computer Vision](https://mlsanity.com/paper/1906.02337/) (2019)

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

- [Adversarial Bayesian Augmentation for Single-Source Domain Generalization](https://mlsanity.com/paper/2307.09520/) (2023)
- [Uncertainty-guided Contrastive Learning for Single Source Domain Generalisation](https://mlsanity.com/paper/2403.07514/) (2024)
- [HCVP: Leveraging Hierarchical Contrastive Visual Prompt for Domain Generalization](https://mlsanity.com/paper/2401.09716/) (2024)
- [Benchmark Generation Framework with Customizable Distortions for Image Classifier Robustness](https://mlsanity.com/paper/2310.18626/) (2023)
- [Improving Shift Invariance in Convolutional Neural Networks with Translation Invariant Polyphase Sampling](https://mlsanity.com/paper/2404.07410/) (2024)
- [Grounding Stylistic Domain Generalization with Quantitative Domain Shift Measures and Synthetic Scene Images](https://mlsanity.com/paper/2405.15961/) (2024)
- [Towards Combating Frequency Simplicity-biased Learning for Domain Generalization](https://mlsanity.com/paper/2410.16146/) (2024)
- [Target-Aware Generative Augmentations for Single-Shot Adaptation](https://mlsanity.com/paper/2305.13284/) (2023)
- [A Novel Cross-Perturbation for Single Domain Generalization](https://mlsanity.com/paper/2308.00918/) (2023)
- [Know Your Space: Inlier and Outlier Construction for Calibrating Medical OOD Detectors](https://mlsanity.com/paper/2207.05286/) (2022)
- [On the Use of Anchoring for Training Vision Models](https://mlsanity.com/paper/2406.00529/) (2024)
- [Causality-inspired Latent Feature Augmentation for Single Domain Generalization](https://mlsanity.com/paper/2406.05980/) (2024)
- [UCDR-Adapter: Exploring Adaptation of Pre-Trained Vision-Language Models for Universal Cross-Domain Retrieval](https://mlsanity.com/paper/2412.10680/) (2024)
- [Variational Learning of Disentangled Representations](https://mlsanity.com/paper/2506.17182/) (2025)
- [ODOV: Benchmark the Open-Domain Open-Vocabulary Object Detection](https://mlsanity.com/paper/2508.01253/) (2025)
- [Patch-aware Batch Normalization for Improving Cross-domain Robustness](https://mlsanity.com/paper/2304.02848/) (2023)

## Abstract (arXiv)

To be successful in single source domain generalization, maximizing diversity of synthesized domains has emerged as one of the most effective strategies. Many of the recent successes have come from methods that pre-specify the types of diversity that a model is exposed to during training, so that it can ultimately generalize well to new domains. However, na"ive diversity based augmentations do not work effectively for domain generalization either because they cannot model large domain shift, or because the span of transforms that are pre-specified do not cover the types of shift commonly occurring in domain generalization. To address this issue, we present a novel framework that uses adversarially learned transformations (ALT) using a neural network to model plausible, yet hard image transformations that fool the classifier. This network is randomly initialized for each batch and trained for a fixed number of steps to maximize classification error. Further, we enforce consistency between the classifier's predictions on the clean and transformed images. With extensive empirical analysis, we find that this new form of adversarial transformations achieve both objectives of diversity and hardness simultaneously, outperforming all existing techniques on competitive benchmarks for single source domain generalization. We also show that ALT can naturally work with existing diversity modules to produce highly distinct, and large transformations of the source domain leading to state-of-the-art performance.