@inbook{00a6bda961114d7ab52d3957b6ac041a,
title = "Extra Domain Data Generation with Generative Adversarial Nets",
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.",
keywords = "Generative adversarial net, data generation, deep neural network",
author = "Luuk Boulogne and Klaas Dijkstra and Marco Wiering",
year = "2019",
month = jan,
day = "28",
doi = "10.1109/SSCI.2018.8628701",
language = "English",
isbn = "9781538692769",
series = "Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",
pages = "1403--1410",
booktitle = "Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018",
note = "SSCI 2018 ; Conference date: 18-11-2018 Through 21-11-2018",
}