Share Email Print

Proceedings Paper

Data augmentation for intra-class imbalance with generative adversarial network
Author(s): Natsuki Hase; Seiya Ito; Naoshi Kaneko; Kazuhiko Sumi
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In classification tasks, the accuracy of classifiers depends on training data. It is known that inter-class imbalanced data degrade the classification accuracy. Previous approaches tend to use data augmentation to solve inter-class imbalance, but the possibility of intra-class imbalance has been ignored. In this paper, we propose a novel method to solve the intra-class imbalance with Generative Adversarial Networks (GAN). The key idea is to examine the distribution of training data in latent space. We experimentally demonstrate that the proposed method generates diverse images and improves classification accuracy on the CIFAR-10 dataset.

Paper Details

Date Published: 16 July 2019
PDF: 8 pages
Proc. SPIE 11172, Fourteenth International Conference on Quality Control by Artificial Vision, 1117206 (16 July 2019); doi: 10.1117/12.2521692
Show Author Affiliations
Natsuki Hase, Aoyama Gakuin Univ. (Japan)
Seiya Ito, Aoyama Gakuin Univ. (Japan)
Naoshi Kaneko, Aoyama Gakuin Univ. (Japan)
Kazuhiko Sumi, Aoyama Gakuin Univ. (Japan)

Published in SPIE Proceedings Vol. 11172:
Fourteenth International Conference on Quality Control by Artificial Vision
Christophe Cudel; Stéphane Bazeille; Nicolas Verrier, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?