Auto-Encoder (AE)-based deep subspace clustering (DSC) methods have achieved impressive performance due to the powerful representation extracted using deep neural networks while prioritizing categorical separability. However, self-reconstruction loss of an AE ignores rich useful relation information and might lead to indiscriminative representation, which inevitably degrades the clustering performance. It is also challenging to learn high-level similarity without feeding semantic labels. Another unsolved problem facing DSC is the huge memory cost due to $n\times n$ similarity matrix, which is incurred by the self-expression layer between an encoder and decoder. To tackle these problems, we use pairwise similarity to weigh the reconstruction loss to capture local structure information, while a similarity is learned by the self-expression layer. Pseudo-graphs and pseudo-labels, which allow benefiting from uncertain knowledge acquired during network training, are further employed to supervise similarity learning. Joint learning and iterative training facilitate to obtain an overall optimal solution. Extensive experiments on benchmark datasets demonstrate the superiority of our approach. By combining with the $k$ -nearest neighbors algorithm, we further show that our method can address the large-scale and out-of-sample problems. The source code of our method is available: https://github.com/sckangz/SelfsupervisedSC .

中文翻译：

---

伪监督深子空间聚类

基于自动编码器 (AE) 的深子空间聚类 (DSC) 方法由于使用深度神经网络提取的强大表示同时优先考虑分类可分性而取得了令人印象深刻的性能。然而，AE 的自重构损失忽略了丰富的有用关系信息，并可能导致不加区分的表示，这不可避免地降低了聚类性能。在不提供语义标签的情况下学习高级相似性也具有挑战性。DSC 面临的另一个未解决的问题是巨大的内存成本 $n\次 n$ 相似度矩阵，由编码器和解码器之间的自我表达层产生。为了解决这些问题，我们使用成对相似度来权衡重建损失以捕获局部结构信息，而相似度则由自我表达层学习。伪图和伪标签可以从网络训练期间获得的不确定知识中受益，进一步用于监督相似性学习。联合学习和迭代训练有助于获得整体最优解。对基准数据集的大量实验证明了我们方法的优越性。通过结合 $千$ -最近邻算法，我们进一步表明我们的方法可以解决大规模和样本外问题。我们方法的源代码是可用的：https://github.com/sckangz/SelfsupervisedSC .