Edinburgh Research Explorer

Augmenting Image Classifiers Using Data Augmentation Generative Adversarial Networks

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

Related Edinburgh Organisations

Open Access permissions

Open

Original languageEnglish
Title of host publicationArtificial Neural Networks and Machine Learning – ICANN 2018
Place of PublicationRhodes, Greece
Pages594-603
Number of pages10
ISBN (Electronic)978-3-030-01424-7
DOIs
Publication statusE-pub ahead of print - 27 Sep 2018
Event27th International Conference on Artificial Neural Networks - Rhodes, Greece
Duration: 4 Oct 20187 Oct 2018
https://e-nns.org/icann2018/

Publication series

NameLecture Notes in Computer Science
Volume11141
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference27th International Conference on Artificial Neural Networks
Abbreviated titleICANN 2018
CountryGreece
CityRhodes
Period4/10/187/10/18
Internet address

Abstract

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.

Event

27th International Conference on Artificial Neural Networks

4/10/187/10/18

Rhodes, Greece

Event: Conference

Download statistics

No data available

ID: 75849248