Quadruplet-Wise Image Similarity Learning

Marc Law 1 Nicolas Thome 1 Matthieu Cord 1
1 MLIA - Machine Learning and Information Access
LIP6 - Laboratoire d'Informatique de Paris 6
Abstract : This paper introduces a novel similarity learning frame-work. Working with inequality constraints involving quadruplets of images, our approach aims at efficiently modeling similarity from rich or complex semantic label relationships. From these quadruplet-wise constraints, we propose a similarity learning framework relying on a con-vex optimization scheme. We then study how our metric learning scheme can exploit specific class relationships, such as class ranking (relative attributes), and class tax-onomy. We show that classification using the learned met-rics gets improved performance over state-of-the-art meth-ods on several datasets. We also evaluate our approach in a new application to learn similarities between webpage screenshots in a fully unsupervised way.
Type de document :
Communication dans un congrès
IEEE International Conference on Computer Vision (ICCV), Dec 2013, Sydney, Australia. pp.249 - 256, 2013, 〈10.1109/ICCV.2013.38〉
Liste complète des métadonnées

Littérature citée [30 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01094069
Contributeur : Marc Law <>
Soumis le : jeudi 11 décembre 2014 - 15:46:55
Dernière modification le : jeudi 22 novembre 2018 - 14:44:28
Document(s) archivé(s) le : jeudi 12 mars 2015 - 10:56:22

Fichier

law_iccv_2013.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Marc Law, Nicolas Thome, Matthieu Cord. Quadruplet-Wise Image Similarity Learning. IEEE International Conference on Computer Vision (ICCV), Dec 2013, Sydney, Australia. pp.249 - 256, 2013, 〈10.1109/ICCV.2013.38〉. 〈hal-01094069〉

Partager

Métriques

Consultations de la notice

217

Téléchargements de fichiers

121