Hybrid Generative-Discriminative Object Recognition
Learning models for detecting and classifying object categories is a challenging problem in machine vision. While discriminative approaches to learning and
classification have, in principle, superior performance, generative approaches
provide many useful features, one of which is the ability to naturally establish
explicit correspondence between model components and scene features this, in
turn, allows for the handling of missing data and unsupervised learning in clutter. We explore a hybrid generative/discriminative approach, using Fisher Kernels [12], which retains most of the desirable properties of generative methods,
while increasing the classification performance through a discriminative setting.
Our experiments, conducted on a number of popular benchmarks, show strong
performance improvements over the corresponding generative approach. In addition, we demonstrate how this hybrid learning paradigm can be extended to
address several outstanding challenges within computer vision including how to
combine multiple object models and learning with unlabelled data.
Learning models for detecting and classifying object categories is a challenging problem in machine vision. While discriminative approaches to learning and
classification have, in principle, superior performance, generative approaches
provide many useful features, one of which is the ability to naturally establish
explicit correspondence between model components and scene features this, in
turn, allows for the handling of missing data and unsupervised learning in clutter. We explore a hybrid generative/discriminative approach, using Fisher Kernels [12], which retains most of the desirable properties of generative methods,
while increasing the classification performance through a discriminative setting.
Our experiments, conducted on a number of popular benchmarks, show strong
performance improvements over the corresponding generative approach. In addition, we demonstrate how this hybrid learning paradigm can be extended to
address several outstanding challenges within computer vision including how to
combine multiple object models and learning with unlabelled data.
Download: pdf
Text Reference
Alex Holub, Max Welling, and Pietro Perona. Hybrid generative-discriminative object recognition. Int. J. Computer Vision, 2007.BibTeX Reference
@article{HolubWP_IJCV_2007,author = "Holub, Alex and Welling, Max and Perona, Pietro",
title = "Hybrid Generative-Discriminative Object Recognition",
journal = "Int. J. Computer Vision",
year = "2007"
}