论文标题
Yurugan：使用生成的对抗网络和聚类小数据集的Yuru-Chara Mascot生成器
YuruGAN: Yuru-Chara Mascot Generator Using Generative Adversarial Networks With Clustering Small Dataset
论文作者
论文摘要
Yuru-Chara是地方政府和公司创建的吉祥物角色，以宣传有关地区和产品的信息。由于创建尤拉查（Yuruchara）需要各种成本，因此可以期待机器学习技术（例如生成对抗网络（GAN））的利用。近年来，据报道，在数据集中使用类条件进行gan训练可以稳定学习并提高生成图像的质量。但是，当原始数据的量很小并且没有给出明确的类时，例如Yuruchara图像，很难应用有条件的gans。在本文中，我们根据聚类和数据增强提出了一个有条件的gan。具体而言，首先，我们在Yuru-Chara Image DataSet上基于K-Means ++进行了聚类，并将其转换为“有条件数据集”。接下来，对有条件数据集进行了数据增强，以使数据量增加了五次。此外，我们构建了一个模型，该模型将重新块和自我发挥作用纳入基于班级有条件的gan的网络，并培训了有条件的Yuru-Chara数据集。通过评估生成的图像，确认了聚类方法差对生成的图像的影响。
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.
