Unsupervised deep clustering via contractive feature representation and focal loss
作者：
Highlights：
• Propose a novel deep clustering framework with joint optimization.
• Learn effective embedded features by contractive representation learning.
• Improve the label assignment mechanism by introducing focal loss.
• Design a mechanism to adopt focal loss into clustering in an unsupervised manner.
摘要
•Propose a novel deep clustering framework with joint optimization.•Learn effective embedded features by contractive representation learning.•Improve the label assignment mechanism by introducing focal loss.•Design a mechanism to adopt focal loss into clustering in an unsupervised manner.
论文关键词：Unsupervised learning,Clustering,Contractive feature representation,Focal loss,Auto-encoder
论文评审过程：Received 25 February 2021, Revised 9 September 2021, Accepted 20 October 2021, Available online 22 October 2021, Version of Record 1 November 2021.
论文官网地址：https://doi.org/10.1016/j.patcog.2021.108386
