Explicit Spatial Encoding for Deep 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%3A00333112" target="_blank" >RIV/68407700:21230/19:00333112 - isvavai.cz</a>
Result on the web
<a href="https://ieeexplore.ieee.org/document/8954243/keywords#keywords" target="_blank" >https://ieeexplore.ieee.org/document/8954243/keywords#keywords</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/CVPR.2019.00962" target="_blank" >10.1109/CVPR.2019.00962</a>
Alternative languages
Result language
angličtina
Original language name
Explicit Spatial Encoding for Deep Local Descriptors
Original language description
We propose a kernelized deep local-patch descriptor based on efficient match kernels of neural network activations. Response of each receptive field is encoded together with its spatial location using explicit feature maps. Two location parametrizations, Cartesian and polar, are used to provide robustness to a different types of canonical patch misalignment. Additionally, we analyze how the conventional architecture, i.e. a fully connected layer attached after the convolutional part, encodes responses in a spatially variant way. In contrary, explicit spatial encoding is used in our descriptor, whose potential applications are not limited to local-patches. We evaluate the descriptor on standard benchmarks. Both versions, encoding 32x32 or 64x64 patches, consistently outperform all other methods on all benchmarks. The number of parameters of the model is independent of the input patch resolution.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
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)
Others
Publication year
2019
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
CVPR 2019: Proceedings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition
ISBN
978-1-7281-3293-8
ISSN
1063-6919
e-ISSN
2575-7075
Number of pages
10
Pages from-to
9386-9395
Publisher name
IEEE
Place of publication
—
Event location
Long Beach
Event date
Jun 15, 2019
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—