mlsanityData to 14 Oct 2026

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

arXiv 2301.07845 ↗First posted 19 Jan 2023cs.CV cs.AIcited by 11

Not on the map. Why?

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.

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

37 of 52 references.

References · 37

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  5. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  6. 2019Invariant Risk Minimizationcited by 1,854
  7. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,264
  8. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,247
  9. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,200
  10. 2020In Search of Lost Domain Generalizationcited by 1,054
  11. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 763
  12. 2013Domain Generalization via Invariant Feature Representationcited by 623
25 more
  1. 2021Domain Generalization with MixStylecited by 566
  2. 2018Generalizing to Unseen Domains via Adversarial Data Augmentationcited by 451
  3. 2020Learning to Generate Novel Domains for Domain Generalizationcited by 296
  4. 2020Deep Domain-Adversarial Image Generation for Domain Generalisationcited by 231
  5. 2021Anticipative Video Transformercited by 200
  6. 2021SelfReg: Self-supervised Contrastive Regularization for Domain Generalizationcited by 189
  7. 2020Learning Joint Spatial-Temporal Transformations for Video Inpaintingcited by 163
  8. 2020Understanding Self-Training for Gradual Domain Adaptationcited by 149
  9. 2019Feature-Critic Networks for Heterogeneous Domain Generalizationcited by 130
  10. 2021CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptationcited by 129
  11. 2021Open Domain Generalization with Domain-Augmented Meta-Learningcited by 115
  12. 2019Generalizing to unseen domains via distribution matchingcited by 110
  13. 2018Best sources forward: domain generalization through source-specific netscited by 82
  14. 2020Towards Universal Representation Learning for Deep Face Recognitioncited by 78
  15. 2020Continuously Indexed Domain Adaptationcited by 75
  16. 2020Learning Invariant Representations and Risks for Semi-supervised Domain Adaptationcited by 69
  17. 2015A Century of Portraits: A Visual Historical Record of American High School Yearbookscited by 54
  18. 2021Domain Invariant Representation Learning with Domain Density Transformationscited by 53
  19. 2017Incremental Adversarial Domain Adaptation for Continually Changing Environmentscited by 52
  20. 2018Multi-component Image Translation for Deep Domain Generalizationcited by 40
  21. 2021Training for the Future: A Simple Gradient Interpolation Loss to Generalize Along Timecited by 28
  22. 2020Domain Generalization via Optimal Transport with Metric Similarity Learningcited by 27
  23. 2020Sequential Learning for Domain Generalizationcited by 26
  24. 2022Generalizing to Evolving Domains with Latent Structure-Aware Sequential Autoencodercited by 19
  25. 2021On the benefits of representation regularization in invariance based domain generalizationcited by 17

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 3; 2025: 4; 2026: 1.

11 papers.

  1. 2024Learning Spectral-Decomposed Tokens for Domain Generalized Semantic Segmentationcited by 22
  2. 2025Learning Robust Spectral Dynamics for Temporal Domain Generalizationcited by 14
  3. 2025ZETA: Leveraging Z-order Curves for Efficient Top-k Attentioncited by 9
  4. 2023Towards Counterfactual Fairness-aware Domain Generalization in Changing Environmentscited by 8
  5. 2023Domain-Generalizable Multiple-Domain Clusteringcited by 7
  6. 2023CODA: Temporal Domain Generalization via Concept Drift Simulatorcited by 6
  7. 2024Non-stationary Domain Generalization: Theory and Algorithmcited by 4
  8. 2024START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformationcited by 4
  9. 2025Let Synthetic Data Shine: Domain Reassembly and Soft-Fusion for Single Domain Generalizationcited by 2
  10. 2025Robust Anomaly Detection Under Normality Distribution Shift in Dynamic Graphscited by 1
  11. 2026FreKoo++: Learning Continuous Spectral Dynamics for Temporal Domain Generalizationcited by 0