Hierarchical Variational Auto-Encoding for Unsupervised Domain Generalization
This addresses the problem of training models that generalize to unseen domains for machine learning practitioners, offering an unsupervised approach that is competitive with supervised methods.
The paper tackles domain generalization by proposing a hierarchical variational autoencoder that learns to disentangle domain-specific from class-specific information without domain supervision during training. The method outperforms previous generative and non-generative approaches in hierarchical domain settings and achieves competitive performance on the PACS benchmark.
We address the task of domain generalization, where the goal is to train a predictive model such that it is able to generalize to a new, previously unseen domain. We choose a hierarchical generative approach within the framework of variational autoencoders and propose a domain-unsupervised algorithm that is able to generalize to new domains without domain supervision. We show that our method is able to learn representations that disentangle domain-specific information from class-label specific information even in complex settings where domain structure is not observed during training. Our interpretable method outperforms previously proposed generative algorithms for domain generalization as well as other non-generative state-of-the-art approaches in several hierarchical domain settings including sequential overlapped near continuous domain shift. It also achieves competitive performance on the standard domain generalization benchmark dataset PACS compared to state-of-the-art approaches which rely on observing domain-specific information during training, as well as another domain unsupervised method. Additionally, we proposed model selection purely based on Evidence Lower Bound (ELBO) and also proposed weak domain supervision where implicit domain information can be added into the algorithm.