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.
翻译: Yuru- chara 是地方政府和公司为发布有关地区和产品的信息而创造的吉祥品。 因为创建 Yuruchara 需要花费很多成本, 因此可以预期使用基因对抗网络( GANs ) 等机器学习技术。 最近几年, 据报道, 在 GAN 培训的数据集中使用类条件可以稳定学习, 提高生成图像的质量 。 但是, 当原始数据数量小, 并且没有给出清晰的类, 如 Yuruchara 图像时, 很难应用等级有条件的 GAN 。 在本文中, 我们建议使用基于集群和数据增强的类有条件的 GAN 。 具体地说, 我们用 yuru- chara 图像数据集的 K- modes++ 进行分组, 并将其转换为类有条件的数据集 。 下一步, 数据增强是在等级有条件的数据集上进行, 这样的数据数量增加了五倍。 此外, 我们建立了一个模型, 将 ResBlock 和自我保存纳入基于 类的 类中基于 IMAN 和 数据增强的分类效果的 GAN, 并培训了 生成的 的 图像的 生成结果 。