Adversarial target-invariant representation learning for domain generalization

11/03/2019
by   Isabela Albuquerque, et al.
0

In many applications of machine learning, the training and test set data come from different distributions, or domains. A number of domain generalization strategies have been introduced with the goal of achieving good performance on out-of-distribution data. In this paper, we propose an adversarial approach to the problem. We propose a process that enforces pair-wise domain invariance while training a feature extractor over a diverse set of domains. We show that this process ensures invariance to any distribution that can be expressed as a mixture of the training domains. Following this insight, we then introduce an adversarial approach in which pair-wise divergences are estimated and minimized. Experiments on two domain generalization benchmarks for object recognition (i.e., PACS and VLCS) show that the proposed method yields higher average accuracy on the target domains in comparison to previously introduced adversarial strategies, as well as recently proposed methods based on learning invariant representations.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/29/2019

Adversarial Invariant Feature Learning with Accuracy Constraint for Domain Generalization

Learning domain-invariant representation is a dominant approach for doma...
research
06/20/2020

Representation via Representations: Domain Generalization via Adversarially Learned Invariant Representations

We investigate the power of censoring techniques, first developed for le...
research
01/21/2021

Out-of-Distribution Generalization Analysis via Influence Function

The mismatch between training and target data is one major challenge for...
research
10/04/2021

Learning Domain-Invariant Relationship with Instrumental Variable for Domain Generalization

Domain generalization (DG) aims to learn from multiple source domains a ...
research
11/18/2019

Domain Generalization Using a Mixture of Multiple Latent Domains

When domains, which represent underlying data distributions, vary during...
research
10/28/2022

Domain Generalization through the Lens of Angular Invariance

Domain generalization (DG) aims at generalizing a classifier trained on ...
research
06/24/2022

Gated Domain Units for Multi-source Domain Generalization

Distribution shift (DS) is a common problem that deteriorates the perfor...

Please sign up or login with your details

Forgot password? Click here to reset