Pairwise Quantization - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2016

Pairwise Quantization

Résumé

We consider the task of lossy compression of high-dimensional vectors through quantization. We propose the approach that learns quantization parameters by minimizing the distortion of scalar products and squared distances between pairs of points. This is in contrast to previous works that obtain these parameters through the minimization of the reconstruction error of individual points. The proposed approach proceeds by finding a linear transformation of the data that effectively reduces the minimization of the pairwise distortions to the minimization of individual reconstruction errors. After such transformation, any of the previously-proposed quantization approaches can be used. Despite the simplicity of this transformation, the experiments demonstrate that it achieves considerable reduction of the pairwise distortions compared to applying quantization directly to the untransformed data.
Fichier principal
Vignette du fichier
PairwiseQuantization.pdf (4.92 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01330582 , version 1 (11-06-2016)

Identifiants

Citer

Artem Babenko, Relja Arandjelovic, Victor Lempitsky. Pairwise Quantization. 2016. ⟨hal-01330582⟩
122 Consultations
171 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More