Fast Discriminative Visual Codebooks using Randomized Clustering Forests

F. Moosmann 1 Bill Triggs 1 Frédéric Jurie 1
1 LEAR - Learning and recognition in vision
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : Some of the most effective recent methods for content-based image classification work by extracting dense or sparse local image descriptors, quantizing them according to a coding rule such as k-means vector quantization, accumulating histograms of the resulting “visual word” codes over the image, and classifying these with a conventional classifier such as an SVM. Large numbers of descriptors and large codebooks are needed for good results and this becomes slow using k-means. We introduce Extremely Randomized Clustering Forests – ensembles of randomly created clustering trees – and show that these provide more accurate results, much faster training and testing and good resistance to background clutter in several state-of-the-art image classification tasks.
Type de document :
Communication dans un congrès
B. Schölkopf, J. Platt and T. Hoffman. Twentieth Annual Conference on Neural Information Processing Systems (NIPS '06), Dec 2006, Vancouver, Canada. MIT Press, pp.985--992, 2007
Liste complète des métadonnées

Littérature citée [24 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-00203734
Contributeur : Hal System <>
Soumis le : lundi 14 janvier 2008 - 16:13:05
Dernière modification le : mardi 5 juin 2018 - 18:00:02
Document(s) archivé(s) le : jeudi 27 septembre 2012 - 14:05:42

Fichier

MTJ-nips06.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

  • HAL Id : hal-00203734, version 1

Collections

IMAG | INRIA | UGA

Citation

F. Moosmann, Bill Triggs, Frédéric Jurie. Fast Discriminative Visual Codebooks using Randomized Clustering Forests. B. Schölkopf, J. Platt and T. Hoffman. Twentieth Annual Conference on Neural Information Processing Systems (NIPS '06), Dec 2006, Vancouver, Canada. MIT Press, pp.985--992, 2007. 〈hal-00203734〉

Partager

Métriques

Consultations de la notice

1382

Téléchargements de fichiers

1543