Domain adaptation meets disentangled representation learning and style transfer

Vu Hoang Tran*, Ching-Chun Huang

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations

Abstract

In this paper, we face the challenges of un-supervised domain adaptation and propose a novel threein-one framework where three tasks domain adaptation, disentangled representation, and style transfer are considered simultaneously. Firstly, the learned features are disentangled into common parts and specific parts. The common parts represent the transferrable features, which are suitable for domain adaptation with less negative transfer. Conversely, the specific parts characterize the unique style of each individual domain. Based on this, the new concept of feature exchange across domains, which can not only enhance the transferability of common features but also be useful for image style transfer, is introduced. These designs allow us to introduce five types of training objectives to realize the three challenging tasks at the same time. The experimental results show that our architecture can be adaptive well to full transfer learning and partial transfer learning upon a well-learned disentangled representation. Besides, the trained network also demonstrates high potential to generate style-transferred images.

Original languageEnglish
Title of host publication2019 IEEE International Conference on Systems, Man and Cybernetics, SMC 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2998-3005
Number of pages8
ISBN (Electronic)9781728145693
DOIs
StatePublished - Oct 2019
Event2019 IEEE International Conference on Systems, Man and Cybernetics, SMC 2019 - Bari, Italy
Duration: 6 Oct 20199 Oct 2019

Publication series

NameConference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
Volume2019-October
ISSN (Print)1062-922X

Conference

Conference2019 IEEE International Conference on Systems, Man and Cybernetics, SMC 2019
Country/TerritoryItaly
CityBari
Period6/10/199/10/19

Fingerprint

Dive into the research topics of 'Domain adaptation meets disentangled representation learning and style transfer'. Together they form a unique fingerprint.

Cite this