Improved deep convolutional embedded clustering with re-selectable sample training

作者：

Highlights：

• This paper proposes an improved deep convolutional embedded clustering algorithm using reliable samples.

• This paper designs the new deep clustering model structure and corresponding loss function.

• In this study, we select reliable samples with pseudo-labels and pass them to the convolutional neural network for training to get a better clustering model.

• We conducted experimental tests on four standard data sets and show the better performance compared to the state-of-the-art clustering algorithms.

摘要

•This paper proposes an improved deep convolutional embedded clustering algorithm using reliable samples.•This paper designs the new deep clustering model structure and corresponding loss function.•In this study, we select reliable samples with pseudo-labels and pass them to the convolutional neural network for training to get a better clustering model.•We conducted experimental tests on four standard data sets and show the better performance compared to the state-of-the-art clustering algorithms.

论文关键词：Unsupervised clustering,Deep embedded clustering,Autoencoder,Reliable samples

论文评审过程：Received 26 January 2021, Revised 10 February 2022, Accepted 24 February 2022, Available online 2 March 2022, Version of Record 15 March 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.108611