Fuzzy based affinity learning for spectral clustering

作者：

Highlights：

• A fuzzy-set based affinity graph construction method is proposed.

• The model is capable of capturing and combining subtle similarity information distributed over discriminative feature subspaces.

• Experiments on different kinds of data show the superiority of the proposed approach compared to other state-of-the-art methods.

摘要

Highlights•A fuzzy-set based affinity graph construction method is proposed.•The model is capable of capturing and combining subtle similarity information distributed over discriminative feature subspaces.•Experiments on different kinds of data show the superiority of the proposed approach compared to other state-of-the-art methods.

论文关键词：Similarity measure,Affinity learning,Spectral clustering,AFS theory

论文评审过程：Received 1 January 2016, Revised 13 June 2016, Accepted 15 June 2016, Available online 18 June 2016, Version of Record 25 June 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.06.011