Domain Adversarial Neural Networks for Domain Generalization: When It Works and How to Improve

02/07/2021
by   Anthony Sicilia, et al.
37

Theoretically, domain adaptation is a well-researched problem. Further, this theory has been well-used in practice. In particular, we note the bound on target error given by Ben-David et al. (2010) and the well-known domain-aligning algorithm based on this work using Domain Adversarial Neural Networks (DANN) presented by Ganin and Lempitsky (2015). Recently, multiple variants of DANN have been proposed for the related problem of domain generalization, but without much discussion of the original motivating bound. In this paper, we investigate the validity of DANN in domain generalization from this perspective. We investigate conditions under which application of DANN makes sense and further consider DANN as a dynamic process during training. Our investigation suggests that the application of DANN to domain generalization may not be as straightforward as it seems. To address this, we design an algorithmic extension to DANN in the domain generalization case. Our experimentation validates both theory and algorithm.

READ FULL TEXT

page 1

page 2

page 3

page 4

06/21/2021

f-Domain-Adversarial Learning: Theory and Algorithms

Unsupervised domain adaptation is used in many machine learning applicat...
01/13/2015

An Improvement to the Domain Adaptation Bound in a PAC-Bayesian context

This paper provides a theoretical analysis of domain adaptation based on...
07/17/2017

PAC-Bayes and Domain Adaptation

We provide two main contributions in PAC-Bayesian theory for domain adap...
04/18/2022

Understanding Gradual Domain Adaptation: Improved Analysis, Optimal Path and Beyond

The vast majority of existing algorithms for unsupervised domain adaptat...
10/03/2019

A General Upper Bound for Unsupervised Domain Adaptation

In this work, we present a novel upper bound of target error to address ...
06/14/2021

KL Guided Domain Adaptation

Domain adaptation is an important problem and often needed for real-worl...
08/30/2022

Super-model ecosystem: A domain-adaptation perspective

This paper attempts to establish the theoretical foundation for the emer...