Skip to main content

Research Repository

Advanced Search

Multiple fake classes GAN for data augmentation in face image dataset.

Ali-Gombe, Adamu; Elyan, Eyad; Jayne, Chrisina


Adamu Ali-Gombe

Chrisina Jayne


Class-imbalanced datasets often contain one or more class that are under-represented in a dataset. In such a situation, learning algorithms are often biased toward the majority class instances. Therefore, some modification to the learning algorithm or the data itself is required before attempting a classification task. Data augmentation is one common approach used to improve the presence of the minority class instances and rebalance the dataset. However, simple augmentation techniques such as applying some affine transformation to the data, may not be sufficient in extreme cases, and often do not capture the variance present in the dataset. In this paper, we propose a new approach to generate more samples from minority class instances based on Generative Adversarial Neural Networks (GAN). We introduce a new Multiple Fake Class Generative Adversarial Networks (MFC-GAN) and generate additional samples to rebalance the dataset. We show that by introducing multiple fake class and oversampling, the model can generate the required minority samples. We evaluate our model on face generation task from attributes using a reduced number of samples in the minority class. Results obtained showed that MFC-GAN produces plausible minority samples that improve the classification performance compared with state-of-the-art ACGAN generated samples.


ALI-GOMBE, A., ELYAN, E. and JAYNE, C. 2019. Multiple fake classes GAN for data augmentation in face image dataset. In Proceedings of the 2019 International joint conference on neural networks (IJCNN 2019), 14-19 July 2019, Budapest, Hungary. Piscataway: IEEE [online], article ID 8851953. Available from:

Conference Name 2019 International joint conference on neural networks (IJCNN 2019)
Conference Location Budapest, Hungary
Start Date Jul 14, 2019
End Date Jul 19, 2019
Acceptance Date Mar 8, 2019
Online Publication Date Sep 30, 2019
Publication Date Sep 30, 2019
Deposit Date Aug 5, 2019
Publicly Available Date Aug 5, 2019
Publisher Institute of Electrical and Electronics Engineers (IEEE)
Series Title Proceedings of International joint conference on neural networks
Series ISSN 2161-4407
Keywords Datasets; Learning algorithms; Generative adversarial neural networks (GAN)
Public URL


You might also like

Downloadable Citations