# DIVA: Domain Invariant Variational Autoencoders

arXiv: https://arxiv.org/abs/1905.10427 · HTML: https://mlsanity.com/paper/1905.10427/

## Key facts

- Cited by 115 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 May 2019.

## Built on by (most cited first, 30 of 115)

- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [Parameter-free Online Test-time Adaptation](https://mlsanity.com/paper/2201.05718/) (2022)
- [Model-Based Domain Generalization](https://mlsanity.com/paper/2102.11436/) (2021)
- [Exploiting Domain-Specific Features to Enhance Domain Generalization](https://mlsanity.com/paper/2110.09410/) (2021)
- [NICO++: Towards Better Benchmarking for Domain Generalization](https://mlsanity.com/paper/2204.08040/) (2022)
- [OOD-GNN: Out-of-Distribution Generalized Graph Neural Network](https://mlsanity.com/paper/2112.03806/) (2021)
- [Probable Domain Generalization via Quantile Risk Minimization](https://mlsanity.com/paper/2207.09944/) (2022)
- [Domain Invariant Representation Learning with Domain Density Transformations](https://mlsanity.com/paper/2102.05082/) (2021)
- [Domain Generalization for Medical Image Analysis: A Review](https://mlsanity.com/paper/2310.08598/) (2023)
- [BayeSeg: Bayesian Modeling for Medical Image Segmentation with Interpretable Generalizability](https://mlsanity.com/paper/2303.01710/) (2023)
- [On the Limitations of Multimodal VAEs](https://mlsanity.com/paper/2110.04121/) (2021)
- [Multiple-environment Self-adaptive Network for Aerial-view Geo-localization](https://mlsanity.com/paper/2204.08381/) (2022)
- [Invariant and Transportable Representations for Anti-Causal Domain Shifts](https://mlsanity.com/paper/2207.01603/) (2022)
- [Semi-supervised Meta-learning with Disentanglement for Domain-generalised Medical Image Segmentation](https://mlsanity.com/paper/2106.13292/) (2021)
- [Graph Domain Adaptation: A Generative View](https://mlsanity.com/paper/2106.07482/) (2021)
- [Anomaly Detection under Distribution Shift](https://mlsanity.com/paper/2303.13845/) (2023)
- [Domain-invariant Feature Exploration for Domain Generalization](https://mlsanity.com/paper/2207.12020/) (2022)
- [Domain Generalization on Medical Imaging Classification using Episodic Training with Task Augmentation](https://mlsanity.com/paper/2106.06908/) (2021)
- [Semantic-Discriminative Mixup for Generalizable Sensor-based Cross-domain Activity Recognition](https://mlsanity.com/paper/2206.06629/) (2022)
- [Domain Generalization in Computational Pathology: Survey and Guidelines](https://mlsanity.com/paper/2310.19656/) (2023)
- [A Bit More Bayesian: Domain-Invariant Learning with Uncertainty](https://mlsanity.com/paper/2105.04030/) (2021)
- [Towards Explaining Distribution Shifts](https://mlsanity.com/paper/2210.10275/) (2022)
- [An Information-theoretic Approach to Distribution Shifts](https://mlsanity.com/paper/2106.03783/) (2021)
- [Aggregating From Multiple Target-Shifted Sources](https://mlsanity.com/paper/2105.04051/) (2021)
- [Fairness and Accuracy under Domain Generalization](https://mlsanity.com/paper/2301.13323/) (2023)
- [On Causally Disentangled Representations](https://mlsanity.com/paper/2112.05746/) (2021)
- [Learning Data Representations with Joint Diffusion Models](https://mlsanity.com/paper/2301.13622/) (2023)
- [Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective](https://mlsanity.com/paper/2208.07365/) (2022)
- [DART: Diversify-Aggregate-Repeat Training Improves Generalization of Neural Networks](https://mlsanity.com/paper/2302.14685/) (2023)
- [Causal Hidden Markov Model for Time Series Disease Forecasting](https://mlsanity.com/paper/2103.16391/) (2021)

## Abstract (arXiv)

We consider the problem of domain generalization, namely, how to learn representations given data from a set of domains that generalize to data from a previously unseen domain. We propose the Domain Invariant Variational Autoencoder (DIVA), a generative model that tackles this problem by learning three independent latent subspaces, one for the domain, one for the class, and one for any residual variations. We highlight that due to the generative nature of our model we can also incorporate unlabeled data from known or previously unseen domains. To the best of our knowledge this has not been done before in a domain generalization setting. This property is highly desirable in fields like medical imaging where labeled data is scarce. We experimentally evaluate our model on the rotated MNIST benchmark and a malaria cell images dataset where we show that (i) the learned subspaces are indeed complementary to each other, (ii) we improve upon recent works on this task and (iii) incorporating unlabelled data can boost the performance even further.