# Feature Stylization and Domain-aware Contrastive Learning for Domain Generalization

arXiv: https://arxiv.org/abs/2108.08596 · HTML: https://mlsanity.com/paper/2108.08596/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- Builds on 49 of its 65 references that are in the map.
- First posted on arXiv 19 Aug 2021.

## Builds on (most cited first, 30 of 49)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Learning Robust Global Representations by Penalizing Local Predictive Power](https://mlsanity.com/paper/1905.13549/) (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)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [Domain Generalization with MixStyle](https://mlsanity.com/paper/2104.02008/) (2021)
- [Domain Generalization by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1903.06864/) (2019)
- [Self-Challenging Improves Cross-Domain Generalization](https://mlsanity.com/paper/2007.02454/) (2020)
- [DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition](https://mlsanity.com/paper/1310.1531/) (2013)
- [Domain Generalization via Model-Agnostic Learning of Semantic Features](https://mlsanity.com/paper/1910.13580/) (2019)
- [Return of Frustratingly Easy Domain Adaptation](https://mlsanity.com/paper/1511.05547/) (2015)
- [Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net](https://mlsanity.com/paper/1807.09441/) (2018)
- [Semi-supervised Domain Adaptation via Minimax Entropy](https://mlsanity.com/paper/1904.06487/) (2019)
- [Unified Deep Supervised Domain Adaptation and Generalization](https://mlsanity.com/paper/1709.10190/) (2017)
- [Learning to Learn Single Domain Generalization](https://mlsanity.com/paper/2003.13216/) (2020)
- [Learning to Generate Novel Domains for Domain Generalization](https://mlsanity.com/paper/2007.03304/) (2020)
- [A Fourier-based Framework for Domain Generalization](https://mlsanity.com/paper/2105.11120/) (2021)
- [Revisiting Batch Normalization For Practical Domain Adaptation](https://mlsanity.com/paper/1603.04779/) (2016)
- [Generalizing Across Domains via Cross-Gradient Training](https://mlsanity.com/paper/1804.10745/) (2018)

## Built on by (most cited first, 30 of 40)

- [Fair Contrastive Learning for Facial Attribute Classification](https://mlsanity.com/paper/2203.16209/) (2022)
- [Test-time Batch Statistics Calibration for Covariate Shift](https://mlsanity.com/paper/2110.04065/) (2021)
- [Fairness and Accuracy under Domain Generalization](https://mlsanity.com/paper/2301.13323/) (2023)
- [MADG: Margin-based Adversarial Learning for Domain Generalization](https://mlsanity.com/paper/2311.08503/) (2023)
- [Domain Generalization via Frequency-domain-based Feature Disentanglement and Interaction](https://mlsanity.com/paper/2201.08029/) (2022)
- [DGMamba: Domain Generalization via Generalized State Space Model](https://mlsanity.com/paper/2404.07794/) (2024)
- [MVDG: A Unified Multi-view Framework for Domain Generalization](https://mlsanity.com/paper/2112.12329/) (2021)
- [Label-Efficient Domain Generalization via Collaborative Exploration and Generalization](https://mlsanity.com/paper/2208.03644/) (2022)
- [Advancing Open-Set Domain Generalization Using Evidential Bi-Level Hardest Domain Scheduler](https://mlsanity.com/paper/2409.17555/) (2024)
- [Diverse Target and Contribution Scheduling for Domain Generalization](https://mlsanity.com/paper/2309.16460/) (2023)
- [Adaptive Domain Generalization via Online Disagreement Minimization](https://mlsanity.com/paper/2208.01996/) (2022)
- [Style Interleaved Learning for Generalizable Person Re-identification](https://mlsanity.com/paper/2207.03132/) (2022)
- [MultiMatch: Multi-task Learning for Semi-supervised Domain Generalization](https://mlsanity.com/paper/2208.05853/) (2022)
- [Cross-Domain Feature Augmentation for Domain Generalization](https://mlsanity.com/paper/2405.08586/) (2024)
- [Inter-subject Contrastive Learning for Subject Adaptive EEG-based Visual Recognition](https://mlsanity.com/paper/2202.02901/) (2022)
- [Source-free Subject Adaptation for EEG-based Visual Recognition](https://mlsanity.com/paper/2301.08448/) (2023)
- [Subject Adaptive EEG-based Visual Recognition](https://mlsanity.com/paper/2110.13470/) (2021)
- [FAMLP: A Frequency-Aware MLP-Like Architecture For Domain Generalization](https://mlsanity.com/paper/2203.12893/) (2022)
- [Resolve Domain Conflicts for Generalizable Remote Physiological Measurement](https://mlsanity.com/paper/2404.07855/) (2024)
- [Non-stationary Domain Generalization: Theory and Algorithm](https://mlsanity.com/paper/2405.06816/) (2024)
- [Learning to Learn Domain-invariant Parameters for Domain Generalization](https://mlsanity.com/paper/2211.04582/) (2022)
- [Domain Generalization for Mammographic Image Analysis with Contrastive Learning](https://mlsanity.com/paper/2304.10226/) (2023)
- [SETA: Semantic-Aware Token Augmentation for Domain Generalization](https://mlsanity.com/paper/2403.11792/) (2024)
- [DG-DETR: Toward Domain Generalized Detection Transformer](https://mlsanity.com/paper/2504.19574/) (2025)
- [Discovering Hierarchy-Grounded Domains with Adaptive Granularity for Clinical Domain Generalization](https://mlsanity.com/paper/2506.06977/) (2025)
- [Learning to Augment via Implicit Differentiation for Domain Generalization](https://mlsanity.com/paper/2210.14271/) (2022)
- [Domain Adversarial Active Learning for Domain Generalization Classification](https://mlsanity.com/paper/2403.06174/) (2024)
- [Unlocking the Potential of Unlabeled Data in Semi-Supervised Domain Generalization](https://mlsanity.com/paper/2503.13915/) (2025)
- [PAID: Pairwise Angular-Invariant Decomposition for Continual Test-Time Adaptation](https://mlsanity.com/paper/2506.02453/) (2025)
- [BiasBed -- Rigorous Texture Bias Evaluation](https://mlsanity.com/paper/2211.13190/) (2022)

## Abstract (arXiv)

Domain generalization aims to enhance the model robustness against domain shift without accessing the target domain. Since the available source domains for training are limited, recent approaches focus on generating samples of novel domains. Nevertheless, they either struggle with the optimization problem when synthesizing abundant domains or cause the distortion of class semantics. To these ends, we propose a novel domain generalization framework where feature statistics are utilized for stylizing original features to ones with novel domain properties. To preserve class information during stylization, we first decompose features into high and low frequency components. Afterward, we stylize the low frequency components with the novel domain styles sampled from the manipulated statistics, while preserving the shape cues in high frequency ones. As the final step, we re-merge both components to synthesize novel domain features. To enhance domain robustness, we utilize the stylized features to maintain the model consistency in terms of features as well as outputs. We achieve the feature consistency with the proposed domain-aware supervised contrastive loss, which ensures domain invariance while increasing class discriminability. Experimental results demonstrate the effectiveness of the proposed feature stylization and the domain-aware contrastive loss. Through quantitative comparisons, we verify the lead of our method upon existing state-of-the-art methods on two benchmarks, PACS and Office-Home.