A Comparative Study of GAN-Generated Handwriting Images and MNIST Images using t-SNE Visualization
It provides an incremental evaluation method for assessing GAN-generated image quality, primarily for researchers in image generation.
This paper tackled the problem of evaluating GAN-generated handwriting images by comparing them to original MNIST images using t-SNE visualization, finding that the generated images were similar but had some distribution differences.
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.