Domain adversarial neural networks for domain generalization: when it works and how to improve

CC BY

Saved in:
Bibliographic Details
Main Authors: Anthony, Sicilia, Xingchen, Zhao, Seong Jae, Hwang
Format: Book
Language:English
Published: Springer 2023
Subjects:
Online Access:https://link.springer.com/article/10.1007/s10994-023-06324-x
https://dlib.phenikaa-uni.edu.vn/handle/PNK/7709
Tags: Add Tag
No Tags, Be the first to tag this record!
id oai:localhost:PNK-7709
record_format dspace
spelling oai:localhost:PNK-77092023-04-10T03:02:34Z Domain adversarial neural networks for domain generalization: when it works and how to improve Anthony, Sicilia Xingchen, Zhao Seong Jae, Hwang DANN) dynamic process during training CC BY 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. (Mach Learn 79(1–2):151–175, 2010) and the well-known domain-aligning algorithm based on this work using Domain Adversarial Neural Networks (DANN) presented by Ganin and Lempitsky (in International conference on machine learning, pp 1180–1189). 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. 2023-04-10T03:02:34Z 2023-04-10T03:02:34Z 2023 Book https://link.springer.com/article/10.1007/s10994-023-06324-x https://dlib.phenikaa-uni.edu.vn/handle/PNK/7709 en application/pdf Springer
institution Digital Phenikaa
collection Digital Phenikaa
language English
topic DANN)
dynamic process during training
spellingShingle DANN)
dynamic process during training
Anthony, Sicilia
Xingchen, Zhao
Seong Jae, Hwang
Domain adversarial neural networks for domain generalization: when it works and how to improve
description CC BY
format Book
author Anthony, Sicilia
Xingchen, Zhao
Seong Jae, Hwang
author_facet Anthony, Sicilia
Xingchen, Zhao
Seong Jae, Hwang
author_sort Anthony, Sicilia
title Domain adversarial neural networks for domain generalization: when it works and how to improve
title_short Domain adversarial neural networks for domain generalization: when it works and how to improve
title_full Domain adversarial neural networks for domain generalization: when it works and how to improve
title_fullStr Domain adversarial neural networks for domain generalization: when it works and how to improve
title_full_unstemmed Domain adversarial neural networks for domain generalization: when it works and how to improve
title_sort domain adversarial neural networks for domain generalization: when it works and how to improve
publisher Springer
publishDate 2023
url https://link.springer.com/article/10.1007/s10994-023-06324-x
https://dlib.phenikaa-uni.edu.vn/handle/PNK/7709
_version_ 1762818480515579904
score 8.891053