Extra Domain Data Generation with Generative Adversarial Nets

  • Luuk Boulogne
  • , Klaas Dijkstra
  • , Marco Wiering

Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

99 Downloads (Pure)

Abstract

This study focuses on supplementing data sets with data of absent classes by using other, similar data sets in which these classes are represented. The data is generated using Gener- ative Adversarial Nets (GANs) trained on the CelebA and MNIST datasets. In particular we use and compare Coupled GANs (CoGANs), Auxiliary Classifier GANs (AC-GANs) and novel a combination of the two (CoAC-GANs) to generate image data of domain-class combinations that were removed from the training data. We also train classifiers on the generated data. The results show that AC-GANs and CoAC-GANs can be used successfully to generate labeled data from domain-class combinations that are absent from the training data. Furthermore, they suggest that the preference for one of the two types of generative models depends on training set characteristics. Classifiers trained on the generated data can accurately classify unseen data from the missing domain-class combinations.
Original languageEnglish
Title of host publicationProceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1403-1410
Number of pages8
ISBN (Print)9781538692769
DOIs
Publication statusPublished - 28-Jan-2019
EventSSCI 2018 - Bangalore, India
Duration: 18-Nov-201821-Nov-2018

Publication series

NameProceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018
Number2
Volume13

Conference

ConferenceSSCI 2018
Country/TerritoryIndia
CityBangalore
Period18/11/201821/11/2018

Keywords

  • Generative adversarial net
  • data generation
  • deep neural network

Fingerprint

Dive into the research topics of 'Extra Domain Data Generation with Generative Adversarial Nets'. Together they form a unique fingerprint.

Cite this