A Comparative Study of GAN-Generated Handwriting Images and MNIST Images using t-SNE Visualization

TL;DR

This paper compares GAN-generated handwritten digit images with original MNIST images using t-SNE visualization, assessing their similarity and differences in feature distribution to evaluate GAN quality.

Contribution

The study introduces a t-SNE based visualization approach to evaluate and compare the distribution of GAN-generated images with original dataset images.

Findings

GAN images are similar to original MNIST images

Differences in feature distribution were observed

t-SNE visualization effectively assesses GAN quality

Abstract

The quality of GAN-generated images on the MNIST dataset was explored in this paper by comparing them to the original images using t-distributed stochastic neighbor embedding (t- SNE) visualization. A GAN was trained with the dataset to generate images and the result of generating all synthetic images, the corresponding labels were saved. The dimensionality of the generated images and the original MNIST dataset was reduced using t-SNE and the resulting embeddings were plotted. The rate of the GAN-generated images was examined by comparing the t-SNE plots of the generated images and the original MNIST images. It was found that the GAN- generated images were similar to the original images but had some differences in the distribution of the features. It is believed that this study provides a useful evaluation method for assessing the quality of GAN-generated images and can help to improve their generation in the future.