IRUS Total

Binary online learned descriptors

File Description SizeFormat 
mikolajczyk.pdfAccepted version1.63 MBAdobe PDFView/Open
Title: Binary online learned descriptors
Authors: Mikolajczyk, KM
Balntas, V
Tang, L
Item Type: Journal Article
Abstract: We propose a novel approach to generate a binary descriptor optimized for each image patch independently. The approach is inspired by the linear discriminant embedding that simultaneously increases inter and decreases intra class distances. A set of discriminative and uncorrelated binary tests is established from all possible tests in an offline training process. The patch adapted descriptors are then efficiently built online from a subset of features which lead to lower intra-class distances and thus, to a more robust descriptor. We perform experiments on three widely used benchmarks and demonstrate improvements in matching performance, and illustrate that per-patch optimization outperforms global optimization.
Issue Date: 1-Mar-2018
Date of Acceptance: 9-Feb-2017
URI: http://hdl.handle.net/10044/1/44750
DOI: 10.1109/TPAMI.2017.2679193
ISSN: 0162-8828
Publisher: Institute of Electrical and Electronics Engineers
Start Page: 555
End Page: 567
Journal / Book Title: IEEE Transactions on Pattern Analysis and Machine Intelligence
Volume: 40
Issue: 3
Copyright Statement: © 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Sponsor/Funder: Engineering & Physical Science Research Council (E
Engineering & Physical Science Research Council (EPSRC)
Funder's Grant Number: EP/N007743/1
Keywords: 0801 Artificial Intelligence and Image Processing
0806 Information Systems
0906 Electrical and Electronic Engineering
Artificial Intelligence & Image Processing
Publication Status: Published
Online Publication Date: 2017-03-19
Appears in Collections:Faculty of Engineering
Electrical and Electronic Engineering