Fast Spectral Ranking for Similarity Search
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F18%3A00327174" target="_blank" >RIV/68407700:21230/18:00327174 - isvavai.cz</a>
Result on the web
<a href="https://ieeexplore.ieee.org/document/8578894" target="_blank" >https://ieeexplore.ieee.org/document/8578894</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/CVPR.2018.00796" target="_blank" >10.1109/CVPR.2018.00796</a>
Alternative languages
Result language
angličtina
Original language name
Fast Spectral Ranking for Similarity Search
Original language description
Despite the success of deep learning on representing images for particular object retrieval, recent studies show that the learned representations still lie on manifolds in a high dimensional space. This makes the Euclidean nearest neighbor search biased for this task. Exploring the manifolds online remains expensive even if a nearest neighbor graph has been computed offline. This work introduces an explicit embedding reducing manifold search to Euclidean search followed by dot product similarity search. This is equivalent to linear graph filtering of a sparse signal in the frequency domain. To speed up online search, we compute an approximate Fourier basis of the graph offline. We improve the state of art on particular object retrieval datasets including the challenging Instre dataset containing small objects. At a scale of 105 images, the offl
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
<a href="/en/project/LL1303" target="_blank" >LL1303: Large Scale Category Retrieval</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2018
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 2018: Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition
ISBN
978-1-5386-6420-9
ISSN
1063-6919
e-ISSN
2575-7075
Number of pages
10
Pages from-to
7632-7641
Publisher name
IEEE
Place of publication
Piscataway, NJ
Event location
Salt Lake City
Event date
Jun 19, 2018
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000457843607081