Memory vectors for similarity search in high-dimensional spaces

Abstract : We study an indexing architecture to store and search in a database of high-dimensional vectors from the perspective of statistical signal processing and decision theory. This architecture is composed of several memory units, each of which summarizes a fraction of the database by a single representative vector. The potential similarity of the query to one of the vectors stored in the memory unit is gauged by a simple correlation with the memory unit's representative vector. This representative optimizes the test of the following hypothesis: the query is independent from any vector in the memory unit vs. the query is a simple perturbation of one of the stored vectors. Compared to exhaustive search, our approach finds the most similar database vectors significantly faster without a noticeable reduction in search quality. Interestingly, the reduction of complexity is provably better in high-dimensional spaces. We empirically demonstrate its practical interest in a large-scale image search scenario with off-the-shelf state-of-the-art descriptors.
Type de document :
Article dans une revue
IEEE Transactions on Big Data, 2017, <10.1109/TBDATA.2017.2677964>
Liste complète des métadonnées
Contributeur : Ahmet Iscen <>
Soumis le : jeudi 2 mars 2017 - 12:40:32
Dernière modification le : mercredi 2 août 2017 - 10:10:34
Document(s) archivé(s) le : mercredi 31 mai 2017 - 13:53:37


Fichiers produits par l'(les) auteur(s)



Ahmet Iscen, Teddy Furon, Vincent Gripon, Michael Rabbat, Hervé Jégou. Memory vectors for similarity search in high-dimensional spaces. IEEE Transactions on Big Data, 2017, <10.1109/TBDATA.2017.2677964>. <hal-01481220>



Consultations de
la notice


Téléchargements du document