High performance person re-identification via a boosting ranking ensemble. (October 2019)

• Record Type: Journal Article
• Authors: Li, Zhaoju; Han, Zhenjun; Xing, Junliang; Ye, Qixiang; Yu, Xuehui; Jiao, Jianbin
• Is Part Of: Pattern recognition. Volume 94(2019:Oct.)
• Page Start: 187
• Page End: 195
• Publication Date: 2019-10
• Subjects: Person re-identification -- Boosting -- Ensemble; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2019.05.022
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: We propose a novel boosting ensemble approach for person Re-id. We formulate the ensemble model for person Re-id from a ranking perspective. We utilize a rectifier loss to enhance the boosting framework to alleviate overfitting. Experimental performance demonstrate the proposed approach achieves superior performance. Abstract: Person re-identification is a very challenging task in computer vision due to severe appearance changes of a person across non-overlapping camera views. It is thus inadequate in most realistic re-identification scenarios to assess similarity using a single metric in a single feature space. Ensemble methods have been proven effective on improving the recognition rate. However, robust combination remains challenging due to the incompatibilities between different distance metrics. In this paper, we propose a novel framework for person re-identification called Boosting Ranking Ensemble (BRE), which adaptively assembles features and metrics from a ranking perspective. To further tackle the overfitting problem, we explore an effective rectifier loss in the proposed BRE framework to alleviate the influence of the misclassified samples. Extensive experimental analyses and evaluations on three commonly adopted benchmarks demonstrate the effectiveness of the proposed method, with superior performance over many state-of-the-art methods.