Kernel Square-Loss Exemplar Machines for Image Retrieval

Rafael Rezende 1 Joaquin Zepeda 2, 3 Jean Ponce 4, 1 Francis Bach 5 Patrick Perez 2
1 WILLOW - Models of visual object recognition and scene understanding
DI-ENS - Département d'informatique de l'École normale supérieure, Inria de Paris
5 SIERRA - Statistical Machine Learning and Parsimony
DI-ENS - Département d'informatique de l'École normale supérieure, ENS Paris - École normale supérieure - Paris, CNRS - Centre National de la Recherche Scientifique, Inria de Paris
Abstract : Zepeda and Pérez have recently demonstrated the promise of the exemplar SVM (ESVM) as a feature encoder for image retrieval. This paper extends this approach in several directions: We first show that replacing the hinge loss by the square loss in the ESVM cost function significantly reduces encoding time with negligible effect on accuracy. We call this model square-loss exemplar machine, or SLEM. We then introduce a kernelized SLEM which can be implemented efficiently through low-rank matrix decomposition , and displays improved performance. Both SLEM variants exploit the fact that the negative examples are fixed, so most of the SLEM computational complexity is relegated to an offline process independent of the positive examples. Our experiments establish the performance and computational advantages of our approach using a large array of base features and standard image retrieval datasets.
Type de document :
Communication dans un congrès
Computer Vision and Pattern Recognition 2017, Jul 2017, Honolulu, United States
Liste complète des métadonnées


https://hal.inria.fr/hal-01515224
Contributeur : Rafael Sampaio de Rezende <>
Soumis le : jeudi 27 avril 2017 - 10:26:54
Dernière modification le : jeudi 15 juin 2017 - 09:09:16

Fichier

SLEM_CVPR2017.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01515224, version 1

Collections

Citation

Rafael Rezende, Joaquin Zepeda, Jean Ponce, Francis Bach, Patrick Perez. Kernel Square-Loss Exemplar Machines for Image Retrieval. Computer Vision and Pattern Recognition 2017, Jul 2017, Honolulu, United States. <hal-01515224>

Partager

Métriques

Consultations de
la notice

294

Téléchargements du document

587