Generative Adversarial Network for Class-Conditional Data Augmentationopen access
- Authors
- Lee, Jeongmin; Yoon, Younkyoung; Kwon, Junseok
- Issue Date
- Dec-2020
- Publisher
- MDPI
- Keywords
- generative adversarial network; data augmentation; image classification
- Citation
- APPLIED SCIENCES-BASEL, v.10, no.23, pp 1 - 15
- Pages
- 15
- Journal Title
- APPLIED SCIENCES-BASEL
- Volume
- 10
- Number
- 23
- Start Page
- 1
- End Page
- 15
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/44015
- DOI
- 10.3390/app10238415
- ISSN
- 2076-3417
2076-3417
- Abstract
- We propose a novel generative adversarial network for class-conditional data augmentation (i.e., GANDA) to mitigate data imbalance problems in image classification tasks. The proposed GANDA generates minority class data by exploiting majority class information to enhance the classification accuracy of minority classes. For stable GAN training, we introduce a new denoising autoencoder initialization with explicit class conditioning in the latent space, which enables the generation of definite samples. The generated samples are visually realistic and have a high resolution. Experimental results demonstrate that the proposed GANDA can considerably improve classification accuracy, especially when datasets are highly imbalanced on standard benchmark datasets (i.e., MNIST and CelebA). Our generated samples can be easily used to train conventional classifiers to enhance their classification accuracy.
- Files in This Item
-
- Appears in
Collections - College of Software > School of Computer Science and Engineering > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.