Data augmentation using fast converging CIELAB-GAN for efficient deep learning dataset generation
by Amin Fadaeddini; Babak Majidi; Alireza Souri; Mohammad Eshghi
International Journal of Computational Science and Engineering (IJCSE), Vol. 26, No. 4, 2023

Abstract: The commercial deep learning applications require large training datasets with many samples from different classes. The generative adversarial networks (GAN) are able to create new data samples for training these machine learning models. However, the low speed of training these GANs in image and multimedia applications is a major constraint. Therefore, in this paper a fast converging GAN called CIELAB-GAN for synthesising new data samples for image data augmentation is proposed. The CIELAB-GAN simplifies the training process of GANs by transforming the images to CIELAB colour space with fewer parameters. Then, the CIELAB-GAN translates the generated grey-scale images into colourised samples using an autoencoder. The experimental results show that the CIELAB-GAN has lower computational complexity of 20% compared to the state of the art GAN models and is able to be trained substantially faster. The proposed CIELAB-GAN can be used for generating new image samples for various deep learning applications.

Online publication date: Wed, 12-Jul-2023

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Computational Science and Engineering (IJCSE):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com