18 May 2018 Learning local feature descriptors through ranking losses improved by variance shrinkage
Author Affiliations +
Abstract
This work proposes an improved ranking model of learning local feature descriptors for matching image patches by introducing a variance shrinkage constraint. Previous ranking losses, such as triplet ranking loss and quadruplet ranking loss, have proven powerful in separating corresponding patch pairs from noncorresponding ones. However, they are unable to restrict the intraclass variation since they are only designed to keep noncorresponding pairs away from corresponding ones. Consequently, those scattered pairs get mixed up near the separating hyperplane, which are difficult to discriminate and may disrupt the performance. To resolve this problem, we introduce a variance shrinkage constraint that aims to reduce the variance of patch pairs in the same class and force them to be close to each other. The combination of ranking losses and the variance shrinkage constraint can efficiently reduce overlaps between patch pairs of different classes, which is confirmed by our experiments. Experiments also show that our model achieves a significant improvement in performance compared with original ranking models and other latest methods.
© 2018 SPIE and IS&T
Dalong Zhang, Dalong Zhang, Lei Zhao, Lei Zhao, Wei Li, Wei Li, Duanqing Xu, Duanqing Xu, Dongming Lu, Dongming Lu, } "Learning local feature descriptors through ranking losses improved by variance shrinkage," Journal of Electronic Imaging 27(3), 033016 (18 May 2018). https://doi.org/10.1117/1.JEI.27.3.033016 . Submission: Received: 27 November 2017; Accepted: 2 May 2018
Received: 27 November 2017; Accepted: 2 May 2018; Published: 18 May 2018
JOURNAL ARTICLE
11 PAGES


SHARE
RELATED CONTENT


Back to Top