Deep Domain-Adversarial Image Generation for Domain Generalisation

Kaiyang Zhou, Yongxin Yang, Timothy Hospedales, Tao Xiang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Machine learning models typically suffer from the domain shift problem when trained on a source dataset and evaluated on a target dataset of different distribution. To overcome this problem, domain generalisation (DG) methods aim to leverage data from multiple source domains so that a trained model can generalise to unseen domains. In this paper, we propose a novel DG approach based on Deep Domain-Adversarial Image Generation (DDAIG). Specifically, DDAIG consists of three components, namely a label classifier, a domain classifier and a domain transformation network (DoTNet). The goal for DoTNet is to map the source training data to unseen domains. This is achieved by having a learning objective formulated to ensure that the generated data can be correctly classified by the label classifier while fooling the domain classifier. By augmenting the source training data with the generated unseen domain data, we can make the label classifier more robust to unknown domain changes. Extensive experiments on four DG datasets demonstrate the effectiveness of our approach.
Original languageEnglish
Title of host publicationProceedings of the AAAI Conference on Artificial Intelligence (AAAI 2020)
PublisherAssociation for the Advancement of Artificial Intelligence AAAI
Pages13025-13032
Number of pages8
ISBN (Print)978-1-57735-835-0
DOIs
Publication statusPublished - 3 Apr 2020
Event34th AAAI Conference on Artificial Intelligence - New York, United States
Duration: 7 Feb 202012 Feb 2020
Conference number: 34
https://aaai.org/Conferences/AAAI-19/

Publication series

Name
PublisherAAAI
Number1-10
Volume34
ISSN (Print)2159-5399
ISSN (Electronic)2374-3468

Conference

Conference34th AAAI Conference on Artificial Intelligence
Abbreviated titleAAAI 2020
Country/TerritoryUnited States
CityNew York
Period7/02/2012/02/20
Internet address

Fingerprint

Dive into the research topics of 'Deep Domain-Adversarial Image Generation for Domain Generalisation'. Together they form a unique fingerprint.

Cite this