Product Quantization for Nearest Neighbor Search - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles IEEE Transactions on Pattern Analysis and Machine Intelligence Year : 2011

Product Quantization for Nearest Neighbor Search

Matthijs Douze
  • Function : Author
  • PersonId : 843109
Cordelia Schmid
  • Function : Author
  • PersonId : 831154


We propose an approximate nearest neighbor search method based on product quantization, which decomposes the space into a Cartesian product of low dimensional subspaces and quantizes each subspace separately. A vector is represented by a short code corresponding to the quantization index. The Euclidean distance between two vectors can be efficiently estimated from their codes. Our method has an advantageous asymmetric version, where an estimated distance is computed between a vector and a code. Our approach is used to search for nearest neighbors efficiently, in particular in combination with an inverted file system. Experiments performed on SIFT and GIST image descriptors show excellent search accuracy outperforming three state-of-the-art approaches. The scalability of our approach is validated on a dataset of two billion vectors.
Fichier principal
Vignette du fichier
paper_hal.pdf (408.73 Ko) Télécharger le fichier
Vignette du fichier
vignette.jpg (15.34 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image

Dates and versions

inria-00514462 , version 1 (23-03-2011)
inria-00514462 , version 2 (22-05-2013)



Hervé Jégou, Matthijs Douze, Cordelia Schmid. Product Quantization for Nearest Neighbor Search. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33 (1), pp.117--128. ⟨10.1109/TPAMI.2010.57⟩. ⟨inria-00514462v1⟩
3986 View
42384 Download



Gmail Facebook X LinkedIn More