Link and code: Fast indexing with graphs and compact regression codes

Abstract : Similarity search approaches based on graph walks have recently attained outstanding speed-accuracy trade-offs, taking aside the memory requirements. In this paper, we revisit these approaches by considering, additionally, the memory constraint required to index billions of images on a single server. This leads us to propose a method based both on graph traversal and compact representations. We encode the indexed vectors using quantization and exploit the graph structure to refine the similarity estimation. In essence, our method takes the best of these two worlds: the search strategy is based on nested graphs, thereby providing high precision with a relatively small set of comparisons. At the same time it offers a significant memory compression. As a result, our approach outperforms the state of the art on operating points considering 64–128 bytes per vector, as demonstrated by our results on two billion-scale public benchmarks.
Type de document :
Communication dans un congrès
CVPR 2018 - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2018, Salt Lake City, United States. IEEE, pp.3646-3654, 〈10.1109/CVPR.2018.00384〉
Liste complète des métadonnées

https://hal.inria.fr/hal-01955971
Contributeur : Alexandre Sablayrolles <>
Soumis le : vendredi 14 décembre 2018 - 17:14:52
Dernière modification le : dimanche 10 mars 2019 - 16:40:35
Document(s) archivé(s) le : vendredi 15 mars 2019 - 16:50:34

Fichier

1804.09996.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Matthijs Douze, Alexandre Sablayrolles, Hervé Jégou. Link and code: Fast indexing with graphs and compact regression codes. CVPR 2018 - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2018, Salt Lake City, United States. IEEE, pp.3646-3654, 〈10.1109/CVPR.2018.00384〉. 〈hal-01955971〉

Partager

Métriques

Consultations de la notice

174

Téléchargements de fichiers

74