# Test-Time Style Shifting: Handling Arbitrary Styles in Domain Generalization

arXiv: https://arxiv.org/abs/2306.04911 · HTML: https://mlsanity.com/paper/2306.04911/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 54 references that are in the map.
- First posted on arXiv 8 Jun 2023.

## Builds on (most cited first, 30 of 34)

- [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)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [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)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [Learning to Generalize: Meta-Learning for Domain Generalization](https://mlsanity.com/paper/1710.03463/) (2017)
- [Out-of-Distribution Generalization via Risk Extrapolation (REx)](https://mlsanity.com/paper/2003.00688/) (2020)
- [Domain Generalization with MixStyle](https://mlsanity.com/paper/2104.02008/) (2021)
- [SWAD: Domain Generalization by Seeking Flat Minima](https://mlsanity.com/paper/2102.08604/) (2021)
- [Self-Challenging Improves Cross-Domain Generalization](https://mlsanity.com/paper/2007.02454/) (2020)
- [A Learned Representation For Artistic Style](https://mlsanity.com/paper/1610.07629/) (2016)
- [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)
- [Generalizing Across Domains via Cross-Gradient Training](https://mlsanity.com/paper/1804.10745/) (2018)
- [Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Data](https://mlsanity.com/paper/1909.00889/) (2019)
- [Episodic Training for Domain Generalization](https://mlsanity.com/paper/1902.00113/) (2019)
- [Domain Generalization by Marginal Transfer Learning](https://mlsanity.com/paper/1711.07910/) (2017)
- [Uncertainty Modeling for Out-of-Distribution Generalization](https://mlsanity.com/paper/2202.03958/) (2022)
- [Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalization](https://mlsanity.com/paper/2203.07740/) (2022)
- [Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification](https://mlsanity.com/paper/2012.00417/) (2020)
- [Learning to Learn with Variational Information Bottleneck for Domain Generalization](https://mlsanity.com/paper/2007.07645/) (2020)
- [On Feature Normalization and Data Augmentation](https://mlsanity.com/paper/2002.11102/) (2020)
- [Permuted AdaIN: Reducing the Bias Towards Global Statistics in Image Classification](https://mlsanity.com/paper/2010.05785/) (2020)

## Built on by (most cited first, 11 of 11)

- [Test-Time Domain Generalization for Face Anti-Spoofing](https://mlsanity.com/paper/2403.19334/) (2024)
- [HYPO: Hyperspherical Out-of-Distribution Generalization](https://mlsanity.com/paper/2402.07785/) (2024)
- [DG-PIC: Domain Generalized Point-In-Context Learning for Point Cloud Understanding](https://mlsanity.com/paper/2407.08801/) (2024)
- [Out-of-Distribution Learning with Human Feedback](https://mlsanity.com/paper/2408.07772/) (2024)
- [Towards Unified and Effective Domain Generalization](https://mlsanity.com/paper/2310.10008/) (2023)
- [Continual Learning for Remote Physiological Measurement: Minimize Forgetting and Simplify Inference](https://mlsanity.com/paper/2407.13974/) (2024)
- [GeneralizeFormer: Layer-Adaptive Model Generation across Test-Time Distribution Shifts](https://mlsanity.com/paper/2502.12195/) (2025)
- [Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights](https://mlsanity.com/paper/2501.03782/) (2025)
- [Decentralized Domain Generalization with Style Sharing: Formal Model and Convergence Analysis](https://mlsanity.com/paper/2504.06235/) (2025)
- [Class-Invariant Test-Time Augmentation for Domain Generalization](https://mlsanity.com/paper/2509.14420/) (2025)
- [UniPET: a universal network for high-quality PET image denoising across varied dose reduction factors](https://mlsanity.com/paper/2606.11131/) (2026)

## Abstract (arXiv)

In domain generalization (DG), the target domain is unknown when the model is being trained, and the trained model should successfully work on an arbitrary (and possibly unseen) target domain during inference. This is a difficult problem, and despite active studies in recent years, it remains a great challenge. In this paper, we take a simple yet effective approach to tackle this issue. We propose test-time style shifting, which shifts the style of the test sample (that has a large style gap with the source domains) to the nearest source domain that the model is already familiar with, before making the prediction. This strategy enables the model to handle any target domains with arbitrary style statistics, without additional model update at test-time. Additionally, we propose style balancing, which provides a great platform for maximizing the advantage of test-time style shifting by handling the DG-specific imbalance issues. The proposed ideas are easy to implement and successfully work in conjunction with various other DG schemes. Experimental results on different datasets show the effectiveness of our methods.