Learning a Distance Metric from Relative Comparisons between Quadruplets of Images

Marc T. Law 1, * Nicolas Thome 1 Matthieu Cord 1
* Auteur correspondant
1 MLIA - Machine Learning and Information Access
LIP6 - Laboratoire d'Informatique de Paris 6
Abstract : This paper is concerned with the problem of learning a distance metric by considering meaningful and dis-criminative distance constraints in some contexts where rich information between data is provided. Classic metric learning approaches focus on constraints that involve pairs or triplets of images. We propose a general Mahalanobis-like distance metric learning framework that exploits distance constraints over up to four different images. We show how the integration of such constraints can lead to unsupervised or semi-supervised learning tasks in some applications. We also show the benefit on recognition performance of this type of constraints, in rich contexts such as relative attributes, class taxonomies and temporal webpage analysis.
Type de document :
Article dans une revue
International Journal of Computer Vision, Springer Verlag, 2016, pp.1-30. 〈10.1007/s11263-016-0923-4〉
Liste complète des métadonnées

Littérature citée [62 références]  Voir  Masquer  Télécharger

https://hal.sorbonne-universite.fr/hal-01346190
Contributeur : Gestionnaire Hal-Upmc <>
Soumis le : lundi 18 juillet 2016 - 14:35:43
Dernière modification le : mardi 11 décembre 2018 - 01:22:15

Fichier

Law_2016_Learning_a_Distance.p...
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Marc T. Law, Nicolas Thome, Matthieu Cord. Learning a Distance Metric from Relative Comparisons between Quadruplets of Images. International Journal of Computer Vision, Springer Verlag, 2016, pp.1-30. 〈10.1007/s11263-016-0923-4〉. 〈hal-01346190〉

Partager

Métriques

Consultations de la notice

238

Téléchargements de fichiers

186