Sparsely grouped multi-task generative adversarial networks for facial attribute manipulation

Jichao Zhang, Gongze Cao, Yezhi Shu, Fan Zhong, Meng Liu, Songhua Xu, Xueying Qin

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

10 Scopus citations

Abstract

Recently, Image-to-Image Translation (IIT) has achieved great progress in image style transfer and semantic context manipulation for images. However, existing approaches require exhaustively labelling training data, which is labor demanding, difficult to scale up, and hard to adapt to a new domain. To overcome such a key limitation, we propose Sparsely Grouped Generative Adversarial Networks (SG-GAN) as a novel approach that can translate images in sparsely grouped datasets where only a few train samples are labelled. Using a one-input multi-output architecture, SG-GAN is well-suited for tackling multi-task learning and sparsely grouped learning tasks. The new model is able to translate images among multiple groups using only a single trained model. To experimentally validate the advantages of the new model, we apply the proposed method to tackle a series of attribute manipulation tasks for facial images as a case study. Experimental results show that SG-GAN can achieve comparable results with state-of-the-art methods on adequately labelled datasets while attaining a superior image translation quality on sparsely grouped datasets.

Original languageEnglish (US)
Title of host publicationMM 2018 - Proceedings of the 2018 ACM Multimedia Conference
PublisherAssociation for Computing Machinery, Inc
Pages392-401
Number of pages10
ISBN (Electronic)9781450356657
DOIs
StatePublished - Oct 15 2018
Event26th ACM Multimedia conference, MM 2018 - Seoul, Korea, Republic of
Duration: Oct 22 2018Oct 26 2018

Publication series

NameMM 2018 - Proceedings of the 2018 ACM Multimedia Conference

Other

Other26th ACM Multimedia conference, MM 2018
Country/TerritoryKorea, Republic of
CitySeoul
Period10/22/1810/26/18

All Science Journal Classification (ASJC) codes

  • Computer Graphics and Computer-Aided Design
  • Human-Computer Interaction

Keywords

  • Deep Learning
  • Generative Adversarial Networks
  • Image Translation

Fingerprint

Dive into the research topics of 'Sparsely grouped multi-task generative adversarial networks for facial attribute manipulation'. Together they form a unique fingerprint.

Cite this