4462 articles – 2360 Notices  [english version]
HAL : inria-00633193, version 2

Voir la fiche détaillée  BibTeX,EndNote,...
Versions disponibles
Anti-sparse coding for approximate nearest neighbor search
Hervé Jégou 1, Teddy Furon 1, Jean-Jacques Fuchs 2
(17/10/2011)

This paper proposes a binarization scheme for vectors of high dimension based on the recent concept of anti-sparse coding, and shows its excellent performance for approximate nearest neighbor search. Unlike other binarization schemes, this framework allows, up to a scaling factor, the explicit reconstruction from the binary representation of the original vector. The paper also shows that random projections which are used in Locality Sensitive Hashing algorithms, are significantly outperformed by regular frames for both synthetic and real data if the number of bits exceeds the vector dimensionality, i.e., when high precision is required.
1 :  TEXMEX (INRIA - IRISA)
CNRS : UMR6074 – INRIA – Institut National des Sciences Appliquées (INSA) - Rennes – Université de Rennes 1
2 :  TEMICS (INRIA - IRISA)
CNRS : UMR6074 – INRIA – Université de Rennes 1
Informatique/Vision par ordinateur et reconnaissance de formes

Informatique/Théorie de l'information et codage

Mathématiques/Théorie de l'information et codage

Informatique/Recherche d'information

Informatique/Base de données
sparse coding – spread representations – approximate neighbors search – Hamming embedding
Liste des fichiers attachés à ce document :
IMG
antisparse.png(54.4 KB)
PDF
RR-7771.pdf(249.4 KB)
PS
RR-7771.ps(1.2 MB)