最大化中心模式和微小模式生成对抗网络

MMMGAN:maximizing middle modes and minor modes in generative adversarial networks

为了解决生成对抗网络(GAN)在生成图像时出现的模式崩塌问题,提出了一种最大化中心模式和微小模式损失生成对抗网络(MMMGAN)。首先,将具有相同标签的生成图像的模式定义为中心模式和微小模式,中心模式和微小模式分别代表相似模式的集合和学习完中心模式后可能的模式变化。其次,基于上述的定义提出最大化中心模式和微小模式损失。最后,引入该损失函数,在保证生成图像的分布逼近真实图像的前提下,绝大多数评价指标都得到了改善,提升了生成图像的多样性。拓展性的实验结果表明,提出的最大化中心模式和微小模式损失应用于两种及其以上不同类型任务中,模式崩塌得到了有效缓解。

In order to mitigate mode collapse when generative adversarial networks(GAN)synthesis images,this paper proposed maximizing middle modes and minor modes in generative adversarial networks(MMMGAN).First of all,MMMGAN defined the mode of the generated images with the identical label as the middle mode and the minor mode.The middle mode and the minor mode separately represented the collection of similar modes and the possible mode changes after learning the middle modes.Secondly,based on the above definition,this paper proposed maximizing middle modes and minor modes loss.Finally,on the premise that the distribution of generated images was possibly close to the real image,MMMGAN improved more than 90%of evaluation metrics and then enhanced diversity of generated images.Extensive experimental results show that the proposed maximizing middle modes and minor modes loss effectively alleviates mode collapse in two or more different types of tasks.