Scalability of the NV-tree: Three Experiments

Laurent Amsaleg, Björn Thór Jónsson, Herwig Lejsek

Publikation: Konference artikel i Proceeding eller bog/rapport kapitelKonferencebidrag i proceedingsForskningpeer review

Abstract

The NV-tree is a scalable approximate high-dimensional indexing method specifically designed for large-scale visual instance search. In this paper, we report on three experiments designed to evaluate the performance of the NV-tree. Two of these experiments embed standard benchmarks within collections of up to 28.5 billion features, representing the largest single-server collection ever reported in the literature. The results show that indeed the NV-tree performs very well for visual instance search applications over large-scale collections.
OriginalsprogEngelsk
TitelProceedings of the International Conference on Similarity Search and Applications (SISAP)
RedaktørerStéphane Marchand-Maillet, Yasin N. Silva, Edgar Chávez
UdgivelsesstedLima, Peru
ForlagSpringer
Publikationsdatookt. 2018
Sider59-72
ISBN (Elektronisk)978-3-030-02223-5
DOI
StatusUdgivet - okt. 2018
NavnLecture Notes in Computer Science
Vol/bind11223
ISSN0302-9743

Emneord

  • High-dimensional indexing
  • Visual instance search
  • Scalable methods
  • Large-scale collections
  • Performance evaluation

Fingeraftryk

Dyk ned i forskningsemnerne om 'Scalability of the NV-tree: Three Experiments'. Sammen danner de et unikt fingeraftryk.

Citationsformater