Scalability of the NV-tree: Three Experiments

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.
Type de document :
Communication dans un congrès
11th International Conference on Similarity Search and Applications, Oct 2018, Lima, Peru
Liste complète des métadonnées

Littérature citée [9 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01843046
Contributeur : Laurent Amsaleg <>
Soumis le : mercredi 18 juillet 2018 - 14:17:41
Dernière modification le : mardi 24 juillet 2018 - 01:08:41

Fichier

nvtree-analysis-SISAP18.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01843046, version 1

Citation

Laurent Amsaleg, Björn Jónsson, Herwig Lejsek. Scalability of the NV-tree: Three Experiments. 11th International Conference on Similarity Search and Applications, Oct 2018, Lima, Peru. 〈hal-01843046〉

Partager

Métriques

Consultations de la notice

135

Téléchargements de fichiers

23