Deep Metric Learning via Facility Location

被引：157

作者：

Song, Hyun Oh ^{[1
]}

Jegelka, Stefanie ^{[2
]}

Rathod, Vivek ^{[1
]}

Murphy, Kevin ^{[1
]}

机构：

[1] Google Res, Mountain View, CA 94043 USA

[2] MIT, Cambridge, MA 02139 USA

来源：

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) | 2017年

关键词：

D O I：

10.1109/CVPR.2017.237

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Learning image similarity metrics in an end-to-end fashion with deep networks has demonstrated excellent results on tasks such as clustering and retrieval. However, current methods, all focus on a very local view of the data. In this paper, we propose a new metric learning scheme, based on structured prediction, that is aware of the global structure of the embedding space, and which is designed to optimize a clustering quality metric (NMI). We show state of the art performance on standard datasets, such as CUB200-2011 [37], Cars196 [18], and Stanford online products [30] on NMI and R@K evaluation metrics.

引用

页码：2206 / 2214

页数：9