# ConstStyle: Robust Domain Generalization with Unified Style Transformation

arXiv: https://arxiv.org/abs/2509.05975 · HTML: https://mlsanity.com/paper/2509.05975/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 31 references that are in the map.
- First posted on arXiv 7 Sep 2025.

## Builds on (most cited first, 23 of 23)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [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)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking](https://mlsanity.com/paper/1609.01775/) (2016)
- [Domain Generalization with MixStyle](https://mlsanity.com/paper/2104.02008/) (2021)
- [Generalizing to Unseen Domains via Adversarial Data Augmentation](https://mlsanity.com/paper/1805.12018/) (2018)
- [Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net](https://mlsanity.com/paper/1807.09441/) (2018)
- [Generalizing Across Domains via Cross-Gradient Training](https://mlsanity.com/paper/1804.10745/) (2018)
- [RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening](https://mlsanity.com/paper/2103.15597/) (2021)
- [Efficient Domain Generalization via Common-Specific Low-Rank Decomposition](https://mlsanity.com/paper/2003.12815/) (2020)
- [Learning to Balance Specificity and Invariance for In and Out of Domain Generalization](https://mlsanity.com/paper/2008.12839/) (2020)
- [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)
- [Permuted AdaIN: Reducing the Bias Towards Global Statistics in Image Classification](https://mlsanity.com/paper/2010.05785/) (2020)
- [Test-time Fourier Style Calibration for Domain Generalization](https://mlsanity.com/paper/2205.06427/) (2022)
- [Rethinking the Evaluation Protocol of Domain Generalization](https://mlsanity.com/paper/2305.15253/) (2023)
- [Domain Generalization via Rationale Invariance](https://mlsanity.com/paper/2308.11158/) (2023)
- [Domain Generalization with Correlated Style Uncertainty](https://mlsanity.com/paper/2212.09950/) (2022)
- [StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization](https://mlsanity.com/paper/2406.00275/) (2024)

## Built on by (most cited first, 1 of 1)

- [Dual Strategies for Test-Time Adaptation](https://mlsanity.com/paper/2604.17542/) (2026)

## Abstract (arXiv)

Deep neural networks often suffer performance drops when test data distribution differs from training data. Domain Generalization (DG) aims to address this by focusing on domain-invariant features or augmenting data for greater diversity. However, these methods often struggle with limited training domains or significant gaps between seen (training) and unseen (test) domains. To enhance DG robustness, we hypothesize that it is essential for the model to be trained on data from domains that closely resemble unseen test domains-an inherently difficult task due to the absence of prior knowledge about the unseen domains. Accordingly, we propose ConstStyle, a novel approach that leverages a unified domain to capture domain-invariant features and bridge the domain gap with theoretical analysis. During training, all samples are mapped onto this unified domain, optimized for seen domains. During testing, unseen domain samples are projected similarly before predictions. By aligning both training and testing data within this unified domain, ConstStyle effectively reduces the impact of domain shifts, even with large domain gaps or few seen domains. Extensive experiments demonstrate that ConstStyle consistently outperforms existing methods across diverse scenarios. Notably, when only a limited number of seen domains are available, ConstStyle can boost accuracy up to 19.82% compared to the next best approach.