Generative Adversarial Networks (GANs) have achieved great success in generating realistic images. Most of these are conditional models, although acquisition of class labels is expensive and time-consuming in practice. To reduce the dependence on labeled data, we propose an un-conditional generative adversarial model, called K-Means-GAN (KM-GAN), which incorporates the idea of updating centers in K-Means into GANs. Specifically, we redesign the framework of GANs by applying K-Means on the features extracted from the discriminator. With obtained labels from K-Means, we propose new objective functions from the perspective of deep metric learning (DML). Distinct from previous works, the discriminator is treated as a feature extractor rather than a classifier in KM-GAN, meanwhile utilization of K-Means makes features of the discriminator more representative. Experiments are conducted on various datasets, such as MNIST, Fashion-10, CIFAR-10 and CelebA, and show that the quality of samples generated by KM-GAN is comparable to some conditional generative adversarial models.
翻译:为了减少对标签数据的依赖,我们提议采用一个无条件的基因对抗模式,称为K-Means-GAN(KM-GAN),将K-Means-GAN(KM-GAN)中心更新为GANs的构想纳入GANs。具体地说,我们重新设计GANs的框架,在从歧视者身上提取的特征上应用K-Means(K-Means)的特征。我们从K-Means获得的标签,从深度计量学习的角度提出了新的客观功能。与以往的作品不同,歧视者被视为一个特征提取器,而不是KMM-GAN的分类器,同时利用K-Means使歧视者的特点更具代表性。我们通过对诸如MNIST、Fashion-10、CIFAR-10和CelibA等各种数据集进行实验,并显示KM-GAN生成的样品质量与某些有条件的基因对抗模型相似。