Energy clustering for unsupervised person re-identification

• DOI: 10.1016/j.imavis.2020.103913
• Publication Date: 2020-04-24T06:28:11Z
• Authors: Kaiwei Zeng; Munan Ning; Yaohua Wang; Yang Guo
• Keywords: Hierarchical clustering; Identification; Complete-linkage clustering; Distance measures

Abstract Due to the high cost of data annotation in supervised person re-identification (re-ID) methods, unsupervised methods become more attractive in the real world. Recently, the hierarchical clustering serves as a promising unsupervised method. One key factor of hierarchical clustering is the distance measurement strategy. Ideally, a good distance measurement should consider both inter-cluster and intra-cluster distance of all samples. To solve this problem, we propose to use the energy distance to measure inter-cluster distance in hierarchical clustering (E-cluster), and use the sum of squares of deviations (SSD) as a regularization term to measure intra-cluster distance for further performance promotion. We evaluate our method on Market-1501 and DukeMTMC-reID. Extensive experiments show that E-cluster obtains significant improvements over the state-of-the-arts fully unsupervised methods.