Large Scale Metric Learning for Distance-Based Image Classification

Thomas Mensink 1, 2, * Jakob Verbeek 1 Florent Perronnin 2 Gabriela Csurka 2
* Auteur correspondant
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : This paper studies large-scale image classification, in a setting where new classes and training images could continuously be added at (near) zero cost. We cast this problem into one of learning a low-rank metric, which is shared across all classes and explore k-nearest neighbor (k-NN) and nearest class mean (NCM) classifiers. We also introduce an extension of the NCM classifier to allow for richer image representations. Experiments on the ImageNet 2010 challenge dataset ---which contains more than 1M training images of 1K classes--- shows, surprisingly, that the NCM classifier compares favorably to the more flexible k-NN classifier. Moreover, the NCM performance suggests that 256 dimensional features is comparable to that of linear SVMs, which were used to obtain the current state-of-the-art performance. Experimentally we study the generalization performance to classes that were not used to learn the metrics, and show how a zero-shot model based on the ImageNet hierarchy can be combined effectively with small training datasets. Using a metric learned on 1K classes, we show results for the ImageNet-10K dataset, and obtain performance that is competitive with the current state-of-the-art, while requiring significant less training time.
Type de document :
Rapport
[Research Report] RR-8077, INRIA. 2012, pp.30
Liste complète des métadonnées

Littérature citée [40 références]  Voir  Masquer  Télécharger


https://hal.inria.fr/hal-00735908
Contributeur : Thoth Team <>
Soumis le : jeudi 27 septembre 2012 - 17:58:53
Dernière modification le : mercredi 11 avril 2018 - 01:59:30
Document(s) archivé(s) le : vendredi 16 décembre 2016 - 18:12:10

Fichiers

RR-8077.pdf
Accord explicite pour ce dépôt

Identifiants

  • HAL Id : hal-00735908, version 1

Collections

Citation

Thomas Mensink, Jakob Verbeek, Florent Perronnin, Gabriela Csurka. Large Scale Metric Learning for Distance-Based Image Classification. [Research Report] RR-8077, INRIA. 2012, pp.30. 〈hal-00735908〉

Partager

Métriques

Consultations de la notice

1141

Téléchargements de fichiers

1464