Data augmentation for intra-class imbalance with generative adversarial network

Natsuki Hase; Seiya Ito; Naoshi Kaneko; Kazuhiko Sumi

doi:10.1117/12.2521692

16 July 2019 Data augmentation for intra-class imbalance with generative adversarial network

Natsuki Hase, Seiya Ito, Naoshi Kaneko, Kazuhiko Sumi

Proceedings Volume 11172, Fourteenth International Conference on Quality Control by Artificial Vision; 1117206 (2019) https://doi.org/10.1117/12.2521692
Event: Fourteenth International Conference on Quality Control by Artificial Vision, 2019, Mulhouse, France

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.

Citation Download Citation

Natsuki Hase, Seiya Ito, Naoshi Kaneko, and Kazuhiko Sumi "Data augmentation for intra-class imbalance with generative adversarial network", Proc. SPIE 11172, Fourteenth International Conference on Quality Control by Artificial Vision, 1117206 (16 July 2019); https://doi.org/10.1117/12.2521692

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available