# Foresee What You Will Learn: Data Augmentation for Domain Generalization in Non-stationary Environment

arXiv: https://arxiv.org/abs/2301.07845 · HTML: https://mlsanity.com/paper/2301.07845/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 52 references that are in the map.
- First posted on arXiv 19 Jan 2023.

## Builds on (most cited first, 30 of 37)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [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)
- [In Search of Lost Domain Generalization](https://mlsanity.com/paper/2007.01434/) (2020)
- [Learning to Generalize: Meta-Learning for Domain Generalization](https://mlsanity.com/paper/1710.03463/) (2017)
- [Domain Generalization via Invariant Feature Representation](https://mlsanity.com/paper/1301.2115/) (2013)
- [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)
- [Learning to Generate Novel Domains for Domain Generalization](https://mlsanity.com/paper/2007.03304/) (2020)
- [Deep Domain-Adversarial Image Generation for Domain Generalisation](https://mlsanity.com/paper/2003.06054/) (2020)
- [Anticipative Video Transformer](https://mlsanity.com/paper/2106.02036/) (2021)
- [SelfReg: Self-supervised Contrastive Regularization for Domain Generalization](https://mlsanity.com/paper/2104.09841/) (2021)
- [Learning Joint Spatial-Temporal Transformations for Video Inpainting](https://mlsanity.com/paper/2007.10247/) (2020)
- [Understanding Self-Training for Gradual Domain Adaptation](https://mlsanity.com/paper/2002.11361/) (2020)
- [Feature-Critic Networks for Heterogeneous Domain Generalization](https://mlsanity.com/paper/1901.11448/) (2019)
- [CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2109.06165/) (2021)
- [Open Domain Generalization with Domain-Augmented Meta-Learning](https://mlsanity.com/paper/2104.03620/) (2021)
- [Generalizing to unseen domains via distribution matching](https://mlsanity.com/paper/1911.00804/) (2019)
- [Best sources forward: domain generalization through source-specific nets](https://mlsanity.com/paper/1806.05810/) (2018)
- [Towards Universal Representation Learning for Deep Face Recognition](https://mlsanity.com/paper/2002.11841/) (2020)
- [Continuously Indexed Domain Adaptation](https://mlsanity.com/paper/2007.01807/) (2020)
- [Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation](https://mlsanity.com/paper/2010.04647/) (2020)
- [A Century of Portraits: A Visual Historical Record of American High School Yearbooks](https://mlsanity.com/paper/1511.02575/) (2015)
- [Domain Invariant Representation Learning with Domain Density Transformations](https://mlsanity.com/paper/2102.05082/) (2021)

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

- [Learning Spectral-Decomposed Tokens for Domain Generalized Semantic Segmentation](https://mlsanity.com/paper/2407.18568/) (2024)
- [Learning Robust Spectral Dynamics for Temporal Domain Generalization](https://mlsanity.com/paper/2505.12585/) (2025)
- [ZETA: Leveraging Z-order Curves for Efficient Top-k Attention](https://mlsanity.com/paper/2501.14577/) (2025)
- [Towards Counterfactual Fairness-aware Domain Generalization in Changing Environments](https://mlsanity.com/paper/2309.13005/) (2023)
- [Domain-Generalizable Multiple-Domain Clustering](https://mlsanity.com/paper/2301.13530/) (2023)
- [CODA: Temporal Domain Generalization via Concept Drift Simulator](https://mlsanity.com/paper/2310.01508/) (2023)
- [Non-stationary Domain Generalization: Theory and Algorithm](https://mlsanity.com/paper/2405.06816/) (2024)
- [START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation](https://mlsanity.com/paper/2410.16020/) (2024)
- [Let Synthetic Data Shine: Domain Reassembly and Soft-Fusion for Single Domain Generalization](https://mlsanity.com/paper/2503.13617/) (2025)
- [Robust Anomaly Detection Under Normality Distribution Shift in Dynamic Graphs](https://mlsanity.com/paper/2509.17400/) (2025)
- [FreKoo++: Learning Continuous Spectral Dynamics for Temporal Domain Generalization](https://mlsanity.com/paper/2608.22224/) (2026)

## Abstract (arXiv)

Existing domain generalization aims to learn a generalizable model to perform well even on unseen domains. For many real-world machine learning applications, the data distribution often shifts gradually along domain indices. For example, a self-driving car with a vision system drives from dawn to dusk, with the sky darkening gradually. Therefore, the system must be able to adapt to changes in ambient illumination and continue to drive safely on the road. In this paper, we formulate such problems as Evolving Domain Generalization, where a model aims to generalize well on a target domain by discovering and leveraging the evolving pattern of the environment. We then propose Directional Domain Augmentation (DDA), which simulates the unseen target features by mapping source data as augmentations through a domain transformer. Specifically, we formulate DDA as a bi-level optimization problem and solve it through a novel meta-learning approach in the representation space. We evaluate the proposed method on both synthetic datasets and realworld datasets, and empirical results show that our approach can outperform other existing methods.