Deep Metric Learning with Online Hard and Soft Selection for Person Re-identification

被引：0

作者：

Yu, Mingyang ^{[1
]}

Kamata, Sei-ichiro ^{[1
,2
]}

机构：

[1] Waseda Univ, Tokyo, Japan

[2] Shanghai Jiao Tong Univ, Shanghai, Peoples R China

来源：

2018 JOINT 7TH INTERNATIONAL CONFERENCE ON INFORMATICS, ELECTRONICS & VISION (ICIEV) AND 2018 2ND INTERNATIONAL CONFERENCE ON IMAGING, VISION & PATTERN RECOGNITION (ICIVPR) | 2018年

关键词：

Deep metric learning; Feature embedding; Person Re-identification;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Deep metric learning has been widely used for image retrieval and verification tasks. Traditional contrastive loss and triplet loss depend highly on the selection of pair/triplet images. It makes the training process unstable and uncomplete. In this paper, we propose a novel global level loss function that considers histograms for intra distances within class and inter distances between different classes. We compared two forms of global level loss (hard selection based loss and soft selection based loss) and both achieved better result than traditional triplet loss, multi class N pair loss and other related works. The experiment is conducted on the person re-identification dataset Market 1501 and DukeMTMC-reID.

引用

页码：426 / 431

页数：6