Skip to Main content Skip to Navigation
Conference papers

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 - Laboratoire d'informatique GRAphique, VIsion et Robotique de Grenoble, 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.
Complete list of metadata

Cited literature [24 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00203734
Contributor : Hal System Connect in order to contact the contributor
Submitted on : Monday, January 14, 2008 - 4:13:05 PM
Last modification on : Wednesday, December 1, 2021 - 12:08:02 AM
Long-term archiving on: : Thursday, September 27, 2012 - 2:05:42 PM

File

MTJ-nips06.pdf
Publisher files allowed on an open archive

Identifiers

  • HAL Id : hal-00203734, version 1

Collections

IMAG | CNRS | INRIA | UGA

Citation

F. Moosmann, Bill Triggs, Frédéric Jurie. Fast Discriminative Visual Codebooks using Randomized Clustering Forests. Twentieth Annual Conference on Neural Information Processing Systems (NIPS '06), Dec 2006, Vancouver, Canada. pp.985--992. ⟨hal-00203734⟩

Share

Metrics

Les métriques sont temporairement indisponibles