Timezone: »

 
Poster
Domain Invariant Representation Learning with Domain Density Transformations
A. Tuan Nguyen · Toan Tran · Yarin Gal · Atilim Gunes Baydin

Tue Dec 07 08:30 AM -- 10:00 AM (PST) @
in Poster Session 1 »

Domain generalization refers to the problem where we aim to train a model on data from a set of source domains so that the model can generalize to unseen target domains. Naively training a model on the aggregate set of data (pooled from all source domains) has been shown to perform suboptimally, since the information learned by that model might be domain-specific and generalize imperfectly to target domains. To tackle this problem, a predominant domain generalization approach is to learn some domain-invariant information for the prediction task, aiming at a good generalization across domains. In this paper, we propose a theoretically grounded method to learn a domain-invariant representation by enforcing the representation network to be invariant under all transformation functions among domains. We next introduce the use of generative adversarial networks to learn such domain transformations in a possible implementation of our method in practice. We demonstrate the effectiveness of our method on several widely used datasets for the domain generalization problem, on all of which we achieve competitive results with state-of-the-art models.

Keywords: Generative Model · Domain Adaptation · Representation Learning

Author Information

A. Tuan Nguyen (University of Oxford)
Toan Tran (Vinai artificial intelligence application and research JSC)
Yarin Gal (University of Oxford)
Atilim Gunes Baydin (University of Oxford)

More from the Same Authors