Scalable Metric Learning via Weighted Approximate Rank Component Analysis

We are interested in the large-scale learning of Mahalanobis distances, with a particular focus on person re-identification. We propose a metric learning formulation called Weighted Approximate Rank Component Analysis (WARCA). WARCA optimizes the precision at top ranks by combining the WARP loss with a regularizer that favors orthonormal linear mappings and avoids rank-deficient embeddings. Using this new regularizer allows us to adapt the large-scale WSABIE procedure and to leverage the Adam stochastic optimization algorithm, which results in an algorithm that scales gracefully to very large data-sets. Also, we derive a kernelized version which allows to take advantage of state-of-the-art features for re-identification when data-set size permits kernel computation. Benchmarks on recent and standard re-identification datasets show that our method beats existing state-of-the-art techniques both in terms of accuracy and speed. We also provide experimental analysis to shade lights on the properties of the regularizer we use, and how it improves performance.


Published in:
Computer Vision - Eccv 2016, Pt V, 9909, 875-890
Presented at:
ECCV 2016
Year:
2016
Publisher:
Cham, Springer Int Publishing Ag
ISSN:
0302-9743
ISBN:
978-3-319-46454-1; 978-3-319-46453-4
Keywords:
Laboratories:




 Record created 2016-07-19, last modified 2018-01-28


Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)