Efficient Image Search with Neural Net Features

D 2015

Efficient Image Search with Neural Net Features

NOVÁK, David, Jan ČECH a Pavel ZEZULA

Základní údaje

Originální název

Efficient Image Search with Neural Net Features

Autoři

NOVÁK, David (203 Česká republika, garant, domácí), Jan ČECH (203 Česká republika) a Pavel ZEZULA (203 Česká republika, domácí)

Vydání

New York, Similarity Search and Applications: 8th International Conference, SISAP 2015, Glasgow, UK, October 12-14, 2015, Proceedings, od s. 237-243, 7 s. 2015

Nakladatel

Springer International Publishing

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

10201 Computer sciences, information science, bioinformatics

Stát vydavatele

Spojené státy

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

tištěná verze "print"

Odkazy

DOI link

Impakt faktor

Impact factor: 0.402 v roce 2005

Kód RIV

RIV/00216224:14330/15:00081692

Organizační jednotka

Fakulta informatiky

ISBN

978-3-319-25086-1

ISSN

DOI

http://dx.doi.org/10.1007/978-3-319-25087-8_22

UT WoS

000374289600022

Klíčová slova anglicky

metric indexing; deep convolutional neural network; contentbased image retrieval

Štítky

content-based image retrieval, DISA, Metric Space

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 28. 4. 2016 15:35, RNDr. Pavel Šmerk, Ph.D.

Anotace

V originále

We present an efficiency evaluation of similarity search techniques applied on visual features from deep neural networks. Our test collection consists of 20 million 4096-dimensional descriptors (320GB of data). We test approximate k-NN search using several techniques, specifically FLANN library (a popular in-memory implementation of k-d tree forest), M-Index (that uses recursive Voronoi partitioning of a metric space), and PPP-Codes, which work with memory codes of metric objects and use disk storage for candidate refinement. Our evaluation shows that as long as the data fit in main memory, the FLANN and the M-Index have practically the same ratio between precision and response time. The PPP-Codes identify candidate sets ten times smaller then the other techniques and the response times are around 500 ms for the whole 20M dataset stored on the disk. The visual search with this index is available as an online demo application. The collection of 20M descriptors is provided as a public dataset to academic community.

Návaznosti

GAP103/10/0886, projekt VaV

Název: Vizuální vyhledávání obrázků na Webu (Akronym: VisualWeb)

Investor: Grantová agentura ČR, Vizuální vyhledávání obrázků na Webu

Citovat

NOVÁK, David, Jan ČECH a Pavel ZEZULA. Efficient Image Search with Neural Net Features. In Similarity Search and Applications: 8th International Conference, SISAP 2015, Glasgow, UK, October 12-14, 2015, Proceedings. New York: Springer International Publishing, 2015, s. 237-243. ISBN 978-3-319-25086-1. Dostupné z: https://dx.doi.org/10.1007/978-3-319-25087-8_22.

@inproceedings{1341689,
   author = {Novák, David and Čech, Jan and Zezula, Pavel},
   address = {New York},
   booktitle = {Similarity Search and Applications: 8th International Conference, SISAP 2015, Glasgow, UK, October 12-14, 2015, Proceedings},
   doi = {http://dx.doi.org/10.1007/978-3-319-25087-8_22},
   keywords = {metric indexing; deep convolutional neural network; contentbased image retrieval},
   howpublished = {tištěná verze "print"},
   language = {eng},
   location = {New York},
   isbn = {978-3-319-25086-1},
   pages = {237-243},
   publisher = {Springer International Publishing},
   title = {Efficient Image Search with Neural Net Features},
   url = {http://dx.doi.org/10.1007/978-3-319-25087-8_22},
   year = {2015}
}

TY  - JOUR
ID  - 1341689
AU  - Novák, David - Čech, Jan - Zezula, Pavel
PY  - 2015
TI  - Efficient Image Search with Neural Net Features
PB  - Springer International Publishing
CY  - New York
SN  - 9783319250861
KW  - metric indexing
KW  - deep convolutional neural network
KW  - contentbased image retrieval
UR  - http://dx.doi.org/10.1007/978-3-319-25087-8_22
L2  - http://dx.doi.org/10.1007/978-3-319-25087-8_22
N2  - We present an efficiency evaluation of similarity search techniques applied on visual features from deep neural networks. Our test collection consists of 20 million 4096-dimensional descriptors (320GB of data). We test approximate k-NN search using several techniques, specifically FLANN library (a popular in-memory implementation of k-d tree forest), M-Index (that uses recursive Voronoi partitioning of a metric space), and PPP-Codes, which work with memory codes of metric objects and use disk storage for candidate refinement. Our evaluation shows that as long as the data fit in main memory, the FLANN and the M-Index have practically the same ratio between precision and response time. The PPP-Codes identify candidate sets ten times smaller then the other techniques and the response times are around 500 ms for the whole 20M dataset stored on the disk. The visual search with this index is available as an online demo application. The collection of 20M descriptors is provided as a public dataset to academic community.
ER  -

NOVÁK, David, Jan ČECH a Pavel ZEZULA. Efficient Image Search with Neural Net Features. In \textit{Similarity Search and Applications: 8th International Conference, SISAP 2015, Glasgow, UK, October 12-14, 2015, Proceedings}. New York: Springer International Publishing, 2015, s.~237-243. ISBN~978-3-319-25086-1. Dostupné z: https://dx.doi.org/10.1007/978-3-319-25087-8\_{}22.

Podrobný výpis o publikaci