Semisupervised Deep Embedded Clustering with Adaptive Labels

Abstract

Deep embedding clustering (DEC) attracts much attention due to its outperforming performance attributed to the end-to-end clustering. However, DEC cannot make use of small amount of a priori knowledge contained in data of increasing volume. To tackle this challenge, a semisupervised deep embedded clustering algorithm with adaptive labels is proposed to cluster those data in a semisupervised end-to-end manner on the basis of a little priori knowledge. Specifically, a deep semisupervised clustering network is designed based on the autoencoder paradigm and deep clustering, which well mine the clustering representation and clustering assignment by preventing the shift of labels in DEC. Then, to train parameters of the deep semisupervised clustering network, a back-propagation-based algorithm with adaptive labels is introduced based on the pretrain and fine-tune strategies. Finally, extensive experiments on representative datasets are conducted to evaluate the performance of the proposed method in terms of clustering accuracy and normalized mutual information. Results show the proposed method outperforms the state-of-the-art methods of DEC.