Large Scale Metric Learning for Distance-Based Image Classification on Open Ended Data Sets

Thomas Mensink 1, 2, * Jakob Verbeek 2, * Florent Perronnin 1, * Gabriela Csurka 1, *
* Auteur correspondant
2 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : Many real-life large-scale datasets are open-ended and dynamic: new images are continuously added to existing classes, new classes appear over time, and the semantics of existing classes might evolve too. Therefore, we study large-scale image classification methods that can incorporate new classes and training images continuously over time at negligible cost. To this end we consider two distance-based classifiers, the k-nearest neighbor (k-NN) and nearest class mean (NCM) classifiers. Since the performance of distance-based classifiers heavily depends on the used distance function, we cast the problem into one of learning a low-rank metric, which is shared across all classes. For the NCM classifier we introduce a new metric learning approach, and we also introduce an extension to allow for richer class representations. Experiments on the ImageNet 2010 challenge dataset, which contains over one million training images of thousand classes, show that, surprisingly, the NCM classifier compares favorably to the more flexible k-NN classifier. Moreover, the NCM performance is comparable to that of linear SVMs which obtain current state-of-the-art performance. Experimentally we study the generalization performance to classes that were not used to learn the metrics. Using a metric learned on 1,000 classes, we show results for the ImageNet-10K dataset which contains 10,000 classes, and obtain performance that is competitive with the current state-of-the-art, while being orders of magnitude faster.
Type de document :
Chapitre d'ouvrage
Farinella, Giovanni Maria and Battiato, Sebastiano and Cipolla, Roberto. Advanced Topics in Computer Vision, Springer, pp.243-276, 2013, 978-1-4471-5519-5. 〈10.1007/978-1-4471-5520-1_9〉
Liste complète des métadonnées

Littérature citée [48 références]  Voir  Masquer  Télécharger


https://hal.inria.fr/hal-00949416
Contributeur : Thoth Team <>
Soumis le : mercredi 19 février 2014 - 16:25:09
Dernière modification le : mercredi 11 avril 2018 - 01:58:12
Document(s) archivé(s) le : lundi 19 mai 2014 - 13:05:50

Fichiers

mensink13atcv.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Thomas Mensink, Jakob Verbeek, Florent Perronnin, Gabriela Csurka. Large Scale Metric Learning for Distance-Based Image Classification on Open Ended Data Sets. Farinella, Giovanni Maria and Battiato, Sebastiano and Cipolla, Roberto. Advanced Topics in Computer Vision, Springer, pp.243-276, 2013, 978-1-4471-5519-5. 〈10.1007/978-1-4471-5520-1_9〉. 〈hal-00949416〉

Partager

Métriques

Consultations de la notice

880

Téléchargements de fichiers

424