# Domain Generalization under Conditional and Label Shifts via Variational Bayesian Inference

arXiv: https://arxiv.org/abs/2107.10931 · HTML: https://mlsanity.com/paper/2107.10931/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 32 references that are in the map.
- First posted on arXiv 22 Jul 2021.

## Builds on (most cited first, 20 of 20)

- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [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)
- [Unified Deep Supervised Domain Adaptation and Generalization](https://mlsanity.com/paper/1709.10190/) (2017)
- [Generalizing Across Domains via Cross-Gradient Training](https://mlsanity.com/paper/1804.10745/) (2018)
- [Episodic Training for Domain Generalization](https://mlsanity.com/paper/1902.00113/) (2019)
- [Domain Generalization Using a Mixture of Multiple Latent Domains](https://mlsanity.com/paper/1911.07661/) (2019)
- [Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift](https://mlsanity.com/paper/2003.04475/) (2020)
- [An introduction to domain adaptation and transfer learning](https://mlsanity.com/paper/1812.11806/) (2018)
- [Learning from Extrinsic and Intrinsic Supervisions for Domain Generalization](https://mlsanity.com/paper/2007.09316/) (2020)
- [Learning to Learn with Variational Information Bottleneck for Domain Generalization](https://mlsanity.com/paper/2007.07645/) (2020)
- [Scatter Component Analysis: A Unified Framework for Domain Adaptation and Domain Generalization](https://mlsanity.com/paper/1510.04373/) (2015)
- [Best sources forward: domain generalization through source-specific nets](https://mlsanity.com/paper/1806.05810/) (2018)
- [Learning to Select Knowledge for Response Generation in Dialog Systems](https://mlsanity.com/paper/1902.04911/) (2019)
- [Domain Generalization via Multidomain Discriminant Analysis](https://mlsanity.com/paper/1907.11216/) (2019)
- [Importance Weighting and Variational Inference](https://mlsanity.com/paper/1808.09034/) (2018)
- [Deep Verifier Networks: Verification of Deep Discriminative Models with Deep Generative Models](https://mlsanity.com/paper/1911.07421/) (2019)
- [Subtype-aware Unsupervised Domain Adaptation for Medical Diagnosis](https://mlsanity.com/paper/2101.00318/) (2021)
- [Causal Generative Domain Adaptation Networks](https://mlsanity.com/paper/1804.04333/) (2018)

## Built on by (most cited first, 18 of 18)

- [Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives](https://mlsanity.com/paper/2208.07422/) (2022)
- [Adversarial Unsupervised Domain Adaptation with Conditional and Label Shift: Infer, Align and Iterate](https://mlsanity.com/paper/2107.13469/) (2021)
- [Domain Generalization in Computational Pathology: Survey and Guidelines](https://mlsanity.com/paper/2310.19656/) (2023)
- [Supervised Algorithmic Fairness in Distribution Shifts: A Survey](https://mlsanity.com/paper/2402.01327/) (2024)
- [ACT: Semi-supervised Domain-adaptive Medical Image Segmentation with Asymmetric Co-training](https://mlsanity.com/paper/2206.02288/) (2022)
- [Domain-Specific Risk Minimization for Out-of-Distribution Generalization](https://mlsanity.com/paper/2208.08661/) (2022)
- [Memory Consistent Unsupervised Off-the-Shelf Model Adaptation for Source-Relaxed Medical Image Segmentation](https://mlsanity.com/paper/2209.07910/) (2022)
- [Domain Generalization in Machine Learning Models for Wireless Communications: Concepts, State-of-the-Art, and Open Issues](https://mlsanity.com/paper/2303.08106/) (2023)
- [Recursively Conditional Gaussian for Ordinal Unsupervised Domain Adaptation](https://mlsanity.com/paper/2107.13467/) (2021)
- [Tackling Long-Tailed Category Distribution Under Domain Shifts](https://mlsanity.com/paper/2207.10150/) (2022)
- [Self-semantic contour adaptation for cross modality brain tumor segmentation](https://mlsanity.com/paper/2201.05022/) (2022)
- [Unsupervised Domain Adaptation for Segmentation with Black-box Source Model](https://mlsanity.com/paper/2208.07769/) (2022)
- [Speech Audio Synthesis from Tagged MRI and Non-Negative Matrix Factorization via Plastic Transformer](https://mlsanity.com/paper/2309.14586/) (2023)
- [Domain Generalization through the Lens of Angular Invariance](https://mlsanity.com/paper/2210.15836/) (2022)
- [Tagged-MRI Sequence to Audio Synthesis via Self Residual Attention Guided Heterogeneous Translator](https://mlsanity.com/paper/2206.02284/) (2022)
- [Bayesian Domain Invariant Learning via Posterior Generalization of Parameter Distributions](https://mlsanity.com/paper/2310.16277/) (2023)
- [Unsupervised Adaptation from FDG to PSMA PET/CT for 3D Lesion Detection under Label Shift](https://mlsanity.com/paper/2603.13666/) (2026)
- [SleepBand: Single-Source Domain Generalization for Sleep Staging via Physiologically Structured Spectral Modeling](https://mlsanity.com/paper/2607.04851/) (2026)

## Abstract (arXiv)

In this work, we propose a domain generalization (DG) approach to learn on several labeled source domains and transfer knowledge to a target domain that is inaccessible in training. Considering the inherent conditional and label shifts, we would expect the alignment of p(x|y) and p(y). However, the widely used domain invariant feature learning (IFL) methods relies on aligning the marginal concept shift w.r.t. p(x), which rests on an unrealistic assumption that p(y) is invariant across domains. We thereby propose a novel variational Bayesian inference framework to enforce the conditional distribution alignment w.r.t. p(x|y) via the prior distribution matching in a latent space, which also takes the marginal label shift w.r.t. p(y) into consideration with the posterior alignment. Extensive experiments on various benchmarks demonstrate that our framework is robust to the label shift and the cross-domain accuracy is significantly improved, thereby achieving superior performance over the conventional IFL counterparts.