YuruGAN: Yuru-Chara Mascot Generator Using Generative Adversarial Networks With Clustering Small Dataset

TL;DR

This paper introduces YuruGAN, a novel approach that combines clustering and data augmentation to enable class-conditional GAN training on small, unlabeled yuru-chara mascot datasets, improving image generation quality.

Contribution

It proposes a clustering-based class conditioning method and data augmentation for GANs applied to small, unlabeled datasets, specifically for yuru-chara mascot images.

Findings

Clustering method impacts generated image quality.

Data augmentation increases dataset size fivefold.

Model with ResBlock and self-attention improves generation.

Abstract

A yuru-chara is a mascot character created by local governments and companies for publicizing information on areas and products. Because it takes various costs to create a yuruchara, the utilization of machine learning techniques such as generative adversarial networks (GANs) can be expected. In recent years, it has been reported that the use of class conditions in a dataset for GANs training stabilizes learning and improves the quality of the generated images. However, it is difficult to apply class conditional GANs when the amount of original data is small and when a clear class is not given, such as a yuruchara image. In this paper, we propose a class conditional GAN based on clustering and data augmentation. Specifically, first, we performed clustering based on K-means++ on the yuru-chara image dataset and converted it into a class conditional dataset. Next, data augmentation was performed on the class conditional dataset so that the amount of data was increased five times. In addition, we built a model that incorporates ResBlock and self-attention into a network based on class conditional GAN and trained the class conditional yuru-chara dataset. As a result of evaluating the generated images, the effect on the generated images by the difference of the clustering method was confirmed.