NV-Tree: nearest neighbors at the billion scale - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2011

NV-Tree: nearest neighbors at the billion scale

Herwig Lejsek
  • Function : Correspondent author
  • PersonId : 914715

Connectez-vous pour contacter l'auteur
Laurent Amsaleg


This paper presents the NV-Tree (Nearest Vector Tree). It addresses the specific, yet important, problem of efficiently and effectively finding the approximate k-nearest neighbors within a collection of a few billion high-dimensional data points. The NV-Tree is a very compact index, as only six bytes are kept in the index for each high-dimensional descriptor. It thus scales extremely well when indexing large collections of high-dimensional descriptors. The NV-Tree efficiently produces results of good quality, even at such a large scale that the indices cannot be kept entirely in main memory any more. We demonstrate this with extensive experiments using a collection of 2.5 billion SIFT (Scale Invariant Feature Transform) descriptors.
No file

Dates and versions

hal-00644939 , version 1 (25-11-2011)



Herwig Lejsek, Björn Þór Jónsson, Laurent Amsaleg. NV-Tree: nearest neighbors at the billion scale. 1st ACM International Conference on Multimedia Retrieval, Apr 2011, Trento, Italy. ⟨10.1145/1991996.1992050⟩. ⟨hal-00644939⟩
257 View
0 Download



Gmail Facebook X LinkedIn More