DeepAI AI Chat
Log In Sign Up

Domain Invariant Representation Learning with Domain Density Transformations

by   A. Tuan Nguyen, et al.

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 approach is to find and learn some domain-invariant information in order to use it for the prediction task. 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 also show how to use generative adversarial networks to learn such domain transformations to implement 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.


page 1

page 2

page 3

page 4


Exploiting Domain-Specific Features to Enhance Domain Generalization

Domain Generalization (DG) aims to train a model, from multiple observed...

Robust Representation Learning with Self-Distillation for Domain Generalization

Domain generalization is a challenging problem in machine learning, wher...

Progressive Domain Expansion Network for Single Domain Generalization

Single domain generalization is a challenging case of model generalizati...

Variational Disentanglement for Domain Generalization

Domain generalization aims to learn an invariant model that can generali...

Domain Generalization with Optimal Transport and Metric Learning

Generalizing knowledge to unseen domains, where data and labels are unav...

Domain Generalization via Multidomain Discriminant Analysis

Domain generalization (DG) aims to incorporate knowledge from multiple s...

DIVA: Domain Invariant Variational Autoencoders

We consider the problem of domain generalization, namely, how to learn r...