mlsanityData to 7 Oct 2026

Causal Inference via Style Transfer for Out-of-distribution Generalisation

arXiv 2212.03063 ↗First posted 6 Dec 2022cs.CV cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

Out-of-distribution (OOD) generalisation aims to build a model that can generalise well on an unseen target domain using knowledge from multiple source domains. To this end, the model should seek the causal dependence between inputs and labels, which may be determined by the semantics of inputs and remain invariant across domains. However, statistical or non-causal methods often cannot capture this dependence and perform poorly due to not considering spurious correlations learnt from model training via unobserved confounders. A well-known existing causal inference method like back-door adjustment cannot be applied to remove spurious correlations as it requires the observation of confounders. In this paper, we propose a novel method that effectively deals with hidden confounders by successfully implementing front-door adjustment (FA). FA requires the choice of a mediator, which we regard as the semantic information of images that helps access the causal mechanism without the need for observing confounders. Further, we propose to estimate the combination of the mediator with other observed images in the front-door formula via style transfer algorithms. Our use of style transfer to estimate FA is novel and sensible for OOD generalisation, which we justify by extensive experimental results on widely used benchmark datasets.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 52 of its 72 references that are in the map. First posted on arXiv 6 Dec 2022.

Builds on

52 of 72 references.

References · 52

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  4. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  5. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,842
  6. 2019Invariant Risk Minimizationcited by 1,832
  7. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
  8. 2017Deeper, Broader and Artier Domain Generalizationcited by 983
  9. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 762
  10. 2021Domain Generalization: A Surveycited by 760
  11. 2013Domain Generalization via Invariant Feature Representationcited by 622
  12. 2021Domain Generalization with MixStylecited by 563
38 more
  1. 2019Domain Generalization by Solving Jigsaw Puzzlescited by 449
  2. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  3. 2020Self-Challenging Improves Cross-Domain Generalizationcited by 426
  4. 2019Domain Generalization via Model-Agnostic Learning of Semantic Featurescited by 405
  5. 2017Unified Deep Supervised Domain Adaptation and Generalizationcited by 322
  6. 2021Self-Supervised Learning with Data Augmentations Provably Isolates Content from Stylecited by 308
  7. 2020Learning to Generate Novel Domains for Domain Generalizationcited by 296
  8. 2021A Fourier-based Framework for Domain Generalizationcited by 287
  9. 2018Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive Learningcited by 278
  10. 2018Generalizing Across Domains via Cross-Gradient Trainingcited by 268
  11. 2020Deep Domain-Adversarial Image Generation for Domain Generalisationcited by 231
  12. 2020Causal Intervention for Weakly-Supervised Semantic Segmentationcited by 229
  13. 2020Domain Generalization using Causal Matchingcited by 224
  14. 2020A Survey on Causal Inferencecited by 202
  15. 2017Neural Style Transfer: A Reviewcited by 199
  16. 2020Representation Learning via Invariant Causal Mechanismscited by 197
  17. 2020Domain Adaptive Ensemble Learningcited by 156
  18. 2016Identifying Causal Effects With Proxy Variables of an Unmeasured Confoundercited by 138
  19. 2022Causality Inspired Representation Learning for Domain Generalizationcited by 136
  20. 2017Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributionscited by 125
  21. 2022Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalizationcited by 122
  22. 2021Causal Attention for Vision-Language Taskscited by 111
  23. 2020Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identificationcited by 110
  24. 2020Visual Commonsense R-CNNcited by 106
  25. 2020Deconfounded Image Captioning: A Causal Retrospectcited by 65
  26. 2020Few-shot Domain Adaptation by Causal Mechanism Transfercited by 47
  27. 2022Out-of-distribution Generalization with Causal Invariant Transformationscited by 45
  28. 2022Harnessing Out-Of-Distribution Examples via Augmenting Content and Stylecited by 43
  29. 2022From Statistical to Causal Learningcited by 40
  30. 2021Transporting Causal Mechanisms for Unsupervised Domain Adaptationcited by 38
  31. 2022Pareto Invariant Risk Minimization: Towards Mitigating the Optimization Dilemma in Out-of-Distribution Generalizationcited by 38
  32. 2022Invariant and Transportable Representations for Anti-Causal Domain Shiftscited by 37
  33. 2021A Bit More Bayesian: Domain-Invariant Learning with Uncertaintycited by 27
  34. 2020Sequential Learning for Domain Generalizationcited by 25
  35. 2022Causal Transportability for Visual Recognitioncited by 23
  36. 2021Deconfounded Visual Groundingcited by 16
  37. 2021Adversarial Visual Robustness by Causal Interventioncited by 13
  38. 2020Random Style Transfer based Domain Generalization Networks Integrating Shape and Spatial Informationcited by 12

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year

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

8 papers.

  1. 2023Domain Generalisation via Risk Distribution Matchingcited by 14
  2. 2024Generalizable Single-Source Cross-modality Medical Image Segmentation via Invariant Causal Mechanismscited by 5
  3. 2024Causality-inspired Latent Feature Augmentation for Single Domain Generalizationcited by 1
  4. 2024DICS: Find Domain-Invariant and Class-Specific Features for Out-of-Distribution Generalizationcited by 1
  5. 2024Causal Fine-Tuning under Latent Confounded Shiftcited by 0
  6. 2025Casual Inference via Style Bias Deconfounding for Domain Generalizationcited by 0
  7. 2025CLEAR: Causal Learning Framework For Robust Histopathology Tumor Detection Under Out-Of-Distribution Shiftscited by 0
  8. 2025CaberNet: Causal Representation Learning for Cross-Domain HVAC Energy Predictioncited by 0