# When Unseen Domain Generalization is Unnecessary? Rethinking Data Augmentation

arXiv: https://arxiv.org/abs/1906.03347 · HTML: https://mlsanity.com/paper/1906.03347/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jun 2019.

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

- [A Fine-Grained Analysis on Distribution Shift](https://mlsanity.com/paper/2110.11328/) (2021)
- [Model-Based Domain Generalization](https://mlsanity.com/paper/2102.11436/) (2021)
- [Towards Principled Disentanglement for Domain Generalization](https://mlsanity.com/paper/2111.13839/) (2021)
- [Generalist Vision Foundation Models for Medical Imaging: A Case Study of Segment Anything Model on Zero-Shot Medical Segmentation](https://mlsanity.com/paper/2304.12637/) (2023)
- [An Empirical Framework for Domain Generalization in Clinical Settings](https://mlsanity.com/paper/2103.11163/) (2021)
- [Learning Domain Invariant Representations for Generalizable Person Re-Identification](https://mlsanity.com/paper/2103.15890/) (2021)
- [Contrastive ACE: Domain Generalization Through Alignment of Causal Mechanisms](https://mlsanity.com/paper/2106.00925/) (2021)
- [Domain Generalization by Rejecting Extreme Augmentations](https://mlsanity.com/paper/2310.06670/) (2023)
- [When Domain Generalization meets Generalized Category Discovery: An Adaptive Task-Arithmetic Driven Approach](https://mlsanity.com/paper/2503.14897/) (2025)
- [Robust One-shot Segmentation of Brain Tissues via Image-aligned Style Transformation](https://mlsanity.com/paper/2211.14521/) (2022)
- [Automatic linear measurements of the fetal brain on MRI with deep neural networks](https://mlsanity.com/paper/2106.08174/) (2021)
- [Explainability-aided Domain Generalization for Image Classification](https://mlsanity.com/paper/2104.01742/) (2021)
- [Bayesian Domain Invariant Learning via Posterior Generalization of Parameter Distributions](https://mlsanity.com/paper/2310.16277/) (2023)
- [Mitigating domain shift in AI-based tuberculosis screening with unsupervised domain adaptation](https://mlsanity.com/paper/2111.04893/) (2021)
- [Adaptive Feature Fusion Neural Network for Glaucoma Segmentation on Unseen Fundus Images](https://mlsanity.com/paper/2404.02084/) (2024)
- [FunduSegmenter: Leveraging the RETFound Foundation Model for Joint Optic Disc and Optic Cup Segmentation in Retinal Fundus Images](https://mlsanity.com/paper/2508.11354/) (2025)

## Abstract (arXiv)

Recent advances in deep learning for medical image segmentation demonstrate expert-level accuracy. However, in clinically realistic environments, such methods have marginal performance due to differences in image domains, including different imaging protocols, device vendors and patient populations. Here we consider the problem of domain generalization, when a model is trained once, and its performance generalizes to unseen domains. Intuitively, within a specific medical imaging modality the domain differences are smaller relative to natural images domain variability. We rethink data augmentation for medical 3D images and propose a deep stacked transformations (DST) approach for domain generalization. Specifically, a series of n stacked transformations are applied to each image in each mini-batch during network training to account for the contribution of domain-specific shifts in medical images. We comprehensively evaluate our method on three tasks: segmentation of whole prostate from 3D MRI, left atrial from 3D MRI, and left ventricle from 3D ultrasound. We demonstrate that when trained on a small source dataset, (i) on average, DST models on unseen datasets degrade only by 11% (Dice score change), compared to the conventional augmentation (degrading 39%) and CycleGAN-based domain adaptation method (degrading 25%); (ii) when evaluation on the same domain, DST is also better albeit only marginally. (iii) When training on large-sized data, DST on unseen domains reaches performance of state-of-the-art fully supervised models. These findings establish a strong benchmark for the study of domain generalization in medical imaging, and can be generalized to the design of robust deep segmentation models for clinical deployment.