Deep clustering incorporates embedding into clustering to find a
lower-dimensional space appropriate for clustering. In this paper, we propose a
novel deep clustering framework with self-supervision using pairwise
similarities (DCSS). The proposed method consists of two successive phases. In
the first phase, we propose to form hypersphere-like groups of similar data
points, i.e. one hypersphere per cluster, employing an autoencoder that is
trained using cluster-specific losses. The hyper-spheres are formed in the
autoencoder's latent space. In the second phase, we propose to employ pairwise
similarities to create a $K$-dimensional space that is capable of accommodating
more complex cluster distributions, hence providing more accurate clustering
performance. $K$ is the number of clusters. The autoencoder's latent space
obtained in the first phase is used as the input of the second phase. The
effectiveness of both phases is demonstrated on seven benchmark datasets by
conducting a rigorous set of experiments.

使用成对相似度的自监督方法提出了一种新颖的深度聚类框架（DCSS），通过形成类似于高维球的相似数据点的群体，并在聚类特定损失下训练自编码器，在自编码器的潜空间中形成超球体，使用自编码器第一阶段得到的潜空间作为第二阶段的输入，通过成对相似度方法在 K 维空间中进行聚类，实验结果表明两个阶段的有效性。