Understanding and Improving Kernel Local Descriptors
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F19%3A00327259" target="_blank" >RIV/68407700:21230/19:00327259 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.1007/s11263-018-1137-8" target="_blank" >https://doi.org/10.1007/s11263-018-1137-8</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/s11263-018-1137-8" target="_blank" >10.1007/s11263-018-1137-8</a>
Alternative languages
Result language
angličtina
Original language name
Understanding and Improving Kernel Local Descriptors
Original language description
We propose a multiple-kernel local-patch descriptor based on efficient match kernels from pixel gradients. It combines two parametrizations of gradient position and direction, each parametrization provides robustness to a different type of patch mis-registration: polar parametrization for noise in the patch dominant orientation detection, Cartesian for imprecise location of the feature point. Combined with whitening of the descriptor space, that is learned with or without supervision, the performance is significantly improved. We analyze the effect of the whitening on patch similarity and demonstrate its semantic meaning. Our unsupervised variant is the best performing descriptor constructed without the need of labeled data. Despite the simplicity of the proposed descriptor, it competes well with deep learning approaches on a number of different tasks.
Czech name
—
Czech description
—
Classification
Type
J<sub>imp</sub> - Article in a specialist periodical, which is included in the Web of Science database
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach
Others
Publication year
2019
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
International Journal of Computer Vision
ISSN
0920-5691
e-ISSN
1573-1405
Volume of the periodical
127
Issue of the periodical within the volume
11-12
Country of publishing house
NL - THE KINGDOM OF THE NETHERLANDS
Number of pages
15
Pages from-to
1723-1737
UT code for WoS article
000492425300009
EID of the result in the Scopus database
2-s2.0-85074163686