# Out-of-Domain Robustness via Targeted Augmentations

arXiv: https://arxiv.org/abs/2302.11861 · HTML: https://mlsanity.com/paper/2302.11861/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 60 references that are in the map.
- First posted on arXiv 23 Feb 2023.

## Builds on (most cited first, 30 of 45)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [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)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [In Search of Lost Domain Generalization](https://mlsanity.com/paper/2007.01434/) (2020)
- [Recognition in Terra Incognita](https://mlsanity.com/paper/1807.04975/) (2018)
- [Underspecification Presents Challenges for Credibility in Modern Machine Learning](https://mlsanity.com/paper/2011.03395/) (2020)
- [Learning to Generate Novel Domains for Domain Generalization](https://mlsanity.com/paper/2007.03304/) (2020)
- [The Risks of Invariant Risk Minimization](https://mlsanity.com/paper/2010.05761/) (2020)
- [Adversarial Domain Adaptation with Domain Mixup](https://mlsanity.com/paper/1912.01805/) (2019)
- [Deep Domain-Adversarial Image Generation for Domain Generalisation](https://mlsanity.com/paper/2003.06054/) (2020)
- [Domain Generalization using Causal Matching](https://mlsanity.com/paper/2006.07500/) (2020)
- [Improving Out-of-Distribution Robustness via Selective Augmentation](https://mlsanity.com/paper/2201.00299/) (2022)
- [Improve Unsupervised Domain Adaptation with Mixup Training](https://mlsanity.com/paper/2001.00677/) (2020)
- [Quantifying the effects of data augmentation and stain color normalization in convolutional neural networks for computational pathology](https://mlsanity.com/paper/1902.06543/) (2019)
- [A Fine-Grained Analysis on Distribution Shift](https://mlsanity.com/paper/2110.11328/) (2021)
- [Correlation Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1612.01939/) (2016)
- [Generalizing to unseen domains via distribution matching](https://mlsanity.com/paper/1911.00804/) (2019)
- [A Kernel Theory of Modern Data Augmentation](https://mlsanity.com/paper/1803.06084/) (2018)
- [Model-Based Domain Generalization](https://mlsanity.com/paper/2102.11436/) (2021)
- [Heterogeneous Domain Generalization via Domain Mixup](https://mlsanity.com/paper/2009.05448/) (2020)
- [InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting](https://mlsanity.com/paper/1908.07801/) (2019)
- [Support and Invertibility in Domain-Invariant Representations](https://mlsanity.com/paper/1903.03448/) (2019)
- [Extending the WILDS Benchmark for Unsupervised Adaptation](https://mlsanity.com/paper/2112.05090/) (2021)
- [Efficient Pipeline for Camera Trap Image Review](https://mlsanity.com/paper/1907.06772/) (2019)

## Built on by (most cited first, 24 of 24)

- [MedMNIST-C: Comprehensive benchmark and improved classifier robustness by simulating realistic image corruptions](https://mlsanity.com/paper/2406.17536/) (2024)
- [Data Augmentations for Improved (Large) Language Model Generalization](https://mlsanity.com/paper/2310.12803/) (2023)
- [Causality and Independence Enhancement for Biased Node Classification](https://mlsanity.com/paper/2310.09586/) (2023)
- [EarthSynth: Generating Informative Earth Observation with Diffusion Models](https://mlsanity.com/paper/2505.12108/) (2025)
- [Reliable Model Watermarking: Defending Against Theft without Compromising on Evasion](https://mlsanity.com/paper/2404.13518/) (2024)
- [Domain constraints improve risk prediction when outcome data is missing](https://mlsanity.com/paper/2312.03878/) (2023)
- [Understanding Domain Generalization: A Noise Robustness Perspective](https://mlsanity.com/paper/2401.14846/) (2024)
- [Connect Later: Improving Fine-tuning for Robustness with Targeted Augmentations](https://mlsanity.com/paper/2402.03325/) (2024)
- [Consistency Regularization for Domain Generalization with Logit Attribution Matching](https://mlsanity.com/paper/2305.07888/) (2023)
- [AutoFT: Learning an Objective for Robust Fine-Tuning](https://mlsanity.com/paper/2401.10220/) (2024)
- [Views Can Be Deceiving: Improved SSL Through Feature Space Augmentation](https://mlsanity.com/paper/2406.18562/) (2024)
- [Dual Risk Minimization: Towards Next-Level Robustness in Fine-tuning Zero-Shot Models](https://mlsanity.com/paper/2411.19757/) (2024)
- [Why Domain Generalization Fail? A View of Necessity and Sufficiency](https://mlsanity.com/paper/2502.10716/) (2025)
- [Test-Time Adaptation by Causal Trimming](https://mlsanity.com/paper/2510.11133/) (2025)
- [Learning Tree-Structured Composition of Data Augmentation](https://mlsanity.com/paper/2408.14381/) (2024)
- [Latent Domain Modeling Improves Robustness to Geographic Shifts](https://mlsanity.com/paper/2503.02036/) (2025)
- [Improving Out-of-Domain Robustness with Targeted Augmentation in Frequency and Pixel Spaces](https://mlsanity.com/paper/2505.12317/) (2025)
- [A Validation Strategy for Deep Learning Models: Evaluating and Enhancing Robustness](https://mlsanity.com/paper/2509.19197/) (2025)
- [HypCBC: Domain-Invariant Hyperbolic Cross-Branch Consistency for Generalizable Medical Image Analysis](https://mlsanity.com/paper/2602.03264/) (2026)
- [Incorporating Interventional Independence Improves Robustness against Interventional Distribution Shift](https://mlsanity.com/paper/2507.05412/) (2025)
- [Universal Adaptive Environment Discovery](https://mlsanity.com/paper/2510.12547/) (2025)
- [D-GAP: Improving Out-of-Domain Robustness via Dataset-Agnostic and Gradient-Guided Augmentation in Frequency and Pixel Spaces](https://mlsanity.com/paper/2511.11286/) (2025)
- [A Causal Framework for Mitigating Data Shifts in Healthcare](https://mlsanity.com/paper/2603.13595/) (2026)
- [Standardizing Medical Images at Scale for AI](https://mlsanity.com/paper/2603.15980/) (2026)

## Abstract (arXiv)

Models trained on one set of domains often suffer performance drops on unseen domains, e.g., when wildlife monitoring models are deployed in new camera locations. In this work, we study principles for designing data augmentations for out-of-domain (OOD) generalization. In particular, we focus on real-world scenarios in which some domain-dependent features are robust, i.e., some features that vary across domains are predictive OOD. For example, in the wildlife monitoring application above, image backgrounds vary across camera locations but indicate habitat type, which helps predict the species of photographed animals. Motivated by theoretical analysis on a linear setting, we propose targeted augmentations, which selectively randomize spurious domain-dependent features while preserving robust ones. We prove that targeted augmentations improve OOD performance, allowing models to generalize better with fewer domains. In contrast, existing approaches such as generic augmentations, which fail to randomize domain-dependent features, and domain-invariant augmentations, which randomize all domain-dependent features, both perform poorly OOD. In experiments on three real-world datasets, we show that targeted augmentations set new states-of-the-art for OOD performance by 3.2-15.2 percentage points.