论文标题
潜在结构对gan的聚类的影响
Effect of The Latent Structure on Clustering with GANs
论文作者
论文摘要
生成的对抗网络（GAN）在来自自然数据歧管（例如图像）的数据中产生了显着的成功。在某种情况下，希望生成的数据得到充分群体，尤其是在存在严重的阶级失衡时。在本文中，我们着重于在生成的gan中聚类的问题，并发现了其与潜在空间特征的关系。我们从第一原理中得出，在GAN框架中实现忠实聚类所需的必要条件：（i）存在具有可调式先验的多模式潜在空间，（ii）存在潜在的群集在潜在的空间上的潜在空间反转机制和（iii）（iii）隔离。我们还通过对多个现实世界图像数据集的消融研究来确定文献中部分满足这些条件并证明所需组件的重要性的GAN模型。此外，我们描述了一个构建多模式潜在空间的程序，该空间促进了稀疏监督的群集研究。
Generative adversarial networks (GANs) have shown remarkable success in generation of data from natural data manifolds such as images. In several scenarios, it is desirable that generated data is well-clustered, especially when there is severe class imbalance. In this paper, we focus on the problem of clustering in generated space of GANs and uncover its relationship with the characteristics of the latent space. We derive from first principles, the necessary and sufficient conditions needed to achieve faithful clustering in the GAN framework: (i) presence of a multimodal latent space with adjustable priors, (ii) existence of a latent space inversion mechanism and (iii) imposition of the desired cluster priors on the latent space. We also identify the GAN models in the literature that partially satisfy these conditions and demonstrate the importance of all the components required, through ablative studies on multiple real world image datasets. Additionally, we describe a procedure to construct a multimodal latent space which facilitates learning of cluster priors with sparse supervision.
