Self-learning for face clustering. (July 2018)

• Record Type: Journal Article
• Authors: Shi, Xiaoshuang; Guo, Zhenhua; Xing, Fuyong; Cai, Jinzheng; Yang, Lin
• Is Part Of: Pattern recognition. Volume 79(2018:Jul.)
• Page Start: 279
• Page End: 289
• Publication Date: 2018-07
• Subjects: Face clustering -- Patch-based two-dimensional reconstruction -- Self-paced learning; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2018.02.008
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: A self-learning framework including image decorrelation and a self-paced learning process, for face clustering. Providing quantitative analysis on the Gaussian distribution of global and local whitening faces. A novel self-paced learning model for face clustering, inspired by the learning process of human. Abstract: In this paper, we simulate the learning way of human to propose a self-learning framework for face clustering. Specifically, we first perform a decorrelation operation on face images through patch-based two-dimensional reconstruction, which has a similar function to the retina. Then we group the semantically similar faces by using a novel self-paced learning model, which is inspired by three major observations: (i) The learning process of human gradually proceeds from easy to complex tasks; (ii) The prior knowledge of human might change with the increase of learned experience; (iii) More prior knowledge usually leads to better prediction accuracy. Experiments on benchmark face databases demonstrate the effectiveness and efficiency of the proposed framework.