Nearest Neighbour Search Using Binary Neural Networks

Demetrio Ferro 1 Vincent Gripon 2, 1 Xiaoran Jiang 1
2 Lab-STICC_TB_CACS_IAS
Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance
Abstract : The problem of finding nearest neighbours in terms of Euclidean distance, Hamming distance or other distance metric is a very common operation in computer vision and pattern recognition. In order to accelerate the search for the nearest neighbour in large collection datasets, many methods rely on the coarse-fine approach. In this paper we propose to combine Product Quantization (PQ) and binary neural associative memories to perform the coarse search. Our motivation lies in the fact that neural network dimensions of the representation associated with a set of k vectors is independent of k. We run experiments on TEXMEX SIFT1M and MNIST databases and observe significant improvements in terms of complexity of the search compared to raw PQ.
Type de document :
Communication dans un congrès
IJCNN 2016 : International Joint Conference on Neural Networks , Jul 2016, Vancouver, Canada. Proceedings IJCNN 2016 : International Joint Conference on Neural Networks pp.5106 - 5112, 2016, 〈10.1109/IJCNN.2016.7727873〉
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01611664
Contributeur : Bibliothèque Télécom Bretagne <>
Soumis le : vendredi 6 octobre 2017 - 11:24:22
Dernière modification le : mercredi 13 juin 2018 - 10:53:54

Identifiants

Citation

Demetrio Ferro, Vincent Gripon, Xiaoran Jiang. Nearest Neighbour Search Using Binary Neural Networks. IJCNN 2016 : International Joint Conference on Neural Networks , Jul 2016, Vancouver, Canada. Proceedings IJCNN 2016 : International Joint Conference on Neural Networks pp.5106 - 5112, 2016, 〈10.1109/IJCNN.2016.7727873〉. 〈hal-01611664〉

Partager

Métriques

Consultations de la notice

56