PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

The NBNN kernel
Tinne Tuytelaars, M. Fritz, K. Saenko and T. Darrell
In: 13th International Conference on Computer Vision, 6-13 November 2011, Barcelona, Spain.

Abstract

Naive Bayes Nearest Neighbor (NBNN) has recently been proposed as a powerful, non-parametric approach for object classification, that manages to achieve remarkably good results thanks to the avoidance of a vector quantization step and the use of image-to-class comparisons, yielding good generalization. In this paper, we introduce a kernelized version of NBNN. This way, we can learn the classifier in a discriminative setting. Moreover, it then becomes straightforward to combine it with other kernels. In particular, we show that our NBNN kernel is complementary to standard bag-of-features based kernels, focussing on local generalization as opposed to global image composition. By combining them, we achieve state-of-the-art results on Caltech101 and 15 Scenes datasets. As a side contribution, we also investigate how to speed up the NBNN computations.

EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
Information Retrieval & Textual Information Access
ID Code:9288
Deposited By:Tinne Tuytelaars
Deposited On:21 February 2012