DiDA: Iterative Boosting of Disentangled Synthesis and Domain Adaptation

Unsupervised domain adaptation aims at learning a shared model for two related domains by leveraging supervision from a source domain to an unsupervised target domain. A number of effective domain adaptation approaches rely on the ability to extract domain-invariant latent factors which are common to both domains. Extracting latent commonality is also useful for disentanglement analysis. It enable...