Paper Info
Title
Learning local feature descriptors through ranking losses improved by variance shrinkage.
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. (C) 2018 SPIE and IS&T
Year
DOI
Venue
2018
10.1117/1.JEI.27.3.033016
JOURNAL OF ELECTRONIC IMAGING
Keywords
Field
DocType
local feature descriptor,image feature,patch matching,convolutional neural network,feature extraction
Ranking,Pattern recognition,Shrinkage,Computer science,Convolutional neural network,Feature extraction,Artificial intelligence,Hyperplane,Local feature descriptor
Journal
Volume
Issue
ISSN
27
3
1017-9909
Citations 
PageRank 
References 
0
0.34
0
Authors
5
Name
Order
Citations
PageRank
jary122.41
Zhao Lei2123.65
Wei Li3382.85
Duanqing Xu47813.16
Dongming Lu516332.29