Implementation of Generative Adversarial Network to Generate Fake Face Image

Abstract

In recent years, many crimes use technology to generate someone's face which has a bad effect on that person. Generative adversarial network is a method to generate fake images using discriminators and generators. Conventional GAN involved binary cross entropy loss for discriminator training to classify original image from dataset and fake image that generated from generator. However, use of binary cross entropy loss cannot provided gradient information to generator in creating a good fake image. When generator creates a fake image, discriminator only gives a little feedback (gradient information) to generator update its model. It causes generator take a long time to update the model. To solve this problem, there is an LSGAN that used a loss function (least squared loss). Discriminator can provide a strong gradient signal to generator update the model even though image was far from decision boundary. In making fake images, researchers used Least Squares GAN (LSGAN) with discriminator-1 loss value is 0.0061, discriminator-2 loss value is 0.0036, and generator loss value is 0.575. With the small loss value of the three important components, discriminator accuracy value in terms of classification reaches 95% for original image and 99% for fake image. In classified original image and fake image in this study using a supervised contrastive loss classification model with an accuracy value of 99.93%.

Keywords

• fake image
• lsgan
• original image
• supervised contrastive loss