Augmenting Image Classifiers Using Data Augmentation Generative Adversarial Networks

Antreas Antoniou, Amos Storkey, Harrison Edwards

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

Abstract / Description of output

Effective training of neural networks requires a lot of data. In the low-data regime, parameters are underdetermined, and learnt networks generalise poorly. Data Augmentation alleviates this by using existing data more effectively. However standard data augmentation produces only limited plausible alternative data. Given there is potential to generate a much broader set of augmentations, we design and train a generative model to do data augmentation. The model, based on image conditional Generative Adversarial Networks, takes data from a source domain and learns to take any data item and augment it by generating other within-class data items. As this generative process does not depend on the classes themselves, it can be applied to novel unseen classes of data. We demonstrate that a Data Augmentation Generative Adversarial Network (DAGAN) augments classiers very well on Omniglot, EMNIST and VGG-Face.
Original languageEnglish
Title of host publicationArtificial Neural Networks and Machine Learning – ICANN 2018
Place of PublicationRhodes, Greece
Number of pages10
ISBN (Electronic)978-3-030-01424-7
Publication statusE-pub ahead of print - 27 Sept 2018
Event27th International Conference on Artificial Neural Networks - Rhodes, Greece
Duration: 4 Oct 20187 Oct 2018

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


Conference27th International Conference on Artificial Neural Networks
Abbreviated titleICANN 2018
Internet address


Dive into the research topics of 'Augmenting Image Classifiers Using Data Augmentation Generative Adversarial Networks'. Together they form a unique fingerprint.

Cite this