# Test-time image-to-image translation ensembling improves out-of-distribution generalization in histopathology

arXiv: https://arxiv.org/abs/2206.09769 · HTML: https://mlsanity.com/paper/2206.09769/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 24 references that are in the map.
- First posted on arXiv 20 Jun 2022.

## Builds on (most cited first, 13 of 13)

- [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)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1804.04732/) (2018)
- [Gradient Matching for Domain Generalization](https://mlsanity.com/paper/2104.09937/) (2021)
- [Quantifying the effects of data augmentation and stain color normalization in convolutional neural networks for computational pathology](https://mlsanity.com/paper/1902.06543/) (2019)
- [StainGAN: Stain Style Transfer for Digital Histological Images](https://mlsanity.com/paper/1804.01601/) (2018)
- [Whole-Slide Mitosis Detection in H&E Breast Histology Using PHH3 as a Reference to Train Distilled Stain-Invariant Convolutional Networks](https://mlsanity.com/paper/1808.05896/) (2018)
- [Structure-Preserving Multi-Domain Stain Color Augmentation using Style-Transfer with Disentangled Representations](https://mlsanity.com/paper/2107.12357/) (2021)
- [Towards Histopathological Stain Invariance by Unsupervised Domain Augmentation using Generative Adversarial Networks](https://mlsanity.com/paper/2012.12413/) (2020)

## Built on by (most cited first, 13 of 13)

- [Domain Generalization for Medical Image Analysis: A Review](https://mlsanity.com/paper/2310.08598/) (2023)
- [A Survey on Domain Generalization for Medical Image Analysis](https://mlsanity.com/paper/2402.05035/) (2024)
- [A Systematic Review of Generalization Research in Medical Image Classification](https://mlsanity.com/paper/2403.12167/) (2024)
- [Towards domain-invariant Self-Supervised Learning with Batch Styles Standardization](https://mlsanity.com/paper/2303.06088/) (2023)
- [Multi-center anatomical segmentation with heterogeneous labels via landmark-based models](https://mlsanity.com/paper/2211.07395/) (2022)
- [HistoStarGAN: A Unified Approach to Stain Normalisation, Stain Transfer and Stain Invariant Segmentation in Renal Histopathology](https://mlsanity.com/paper/2210.09798/) (2022)
- [A Laplacian Pyramid Based Generative H&E Stain Augmentation Network](https://mlsanity.com/paper/2305.14301/) (2023)
- [Learning from Random Subspace Exploration: Generalized Test-Time Augmentation with Self-supervised Distillation](https://mlsanity.com/paper/2507.01347/) (2025)
- [ALFA -- Leveraging All Levels of Feature Abstraction for Enhancing the Generalization of Histopathology Image Classification Across Unseen Hospitals](https://mlsanity.com/paper/2308.03936/) (2023)
- [Stain Consistency Learning: Handling Stain Variation for Automatic Digital Pathology Segmentation](https://mlsanity.com/paper/2311.06552/) (2023)
- [PathoWAve: A Deep Learning-based Weight Averaging Method for Improving Domain Generalization in Histopathology Images](https://mlsanity.com/paper/2406.15685/) (2024)
- [Learning Semantic Directions for Feature Augmentation in Domain-Generalized Medical Segmentation](https://mlsanity.com/paper/2507.23326/) (2025)
- [Value bounds and Convergence Analysis for Averages of LRP attributions](https://mlsanity.com/paper/2509.08963/) (2025)

## Abstract (arXiv)

Histopathology whole slide images (WSIs) can reveal significant inter-hospital variability such as illumination, color or optical artifacts. These variations, caused by the use of different scanning protocols across medical centers (staining, scanner), can strongly harm algorithms generalization on unseen protocols. This motivates development of new methods to limit such drop of performances. In this paper, to enhance robustness on unseen target protocols, we propose a new test-time data augmentation based on multi domain image-to-image translation. It allows to project images from unseen protocol into each source domain before classifying them and ensembling the predictions. This test-time augmentation method results in a significant boost of performances for domain generalization. To demonstrate its effectiveness, our method has been evaluated on 2 different histopathology tasks where it outperforms conventional domain generalization, standard H&E specific color augmentation/normalization and standard test-time augmentation techniques. Our code is publicly available at https://gitlab.com/vitadx/articles/test-time-i2i-translation-ensembling.