Scalability of the NV-tree: Three Experiments

Laurent Amsaleg, Björn Thór Jónsson, Herwig Lejsek

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review


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.
Original languageEnglish
Title of host publicationProceedings of the International Conference on Similarity Search and Applications (SISAP)
EditorsStéphane Marchand-Maillet, Yasin N. Silva, Edgar Chávez
Place of PublicationLima, Peru
Publication dateOct 2018
ISBN (Electronic)978-3-030-02223-5
Publication statusPublished - Oct 2018
SeriesLecture Notes in Computer Science


Dive into the research topics of 'Scalability of the NV-tree: Three Experiments'. Together they form a unique fingerprint.

Cite this