Combining Generative Models and Fisher Kernels for 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  which retains most of the desirable properties of generative methods, while increasing the classification performance through a discriminative setting. Furthermore, we demonstrate how this kernel framework can be used to combine different types of features and models into a single classifier. Our experiments, conducted on a number of popular benchmarks, show strong performance improvements over the corresponding generative approach and are competitive with the best results reported in the literature.
Text ReferenceAlex D. Holub, Max Welling, and Pietro Perona. Combining generative models and fisher kernels for object recognition. In ICCV, I: 136–143. 2005.
AUTHOR = "Holub, Alex D. and Welling, Max and Perona, Pietro",
TAG = "object_recognition",
TITLE = "Combining Generative Models and Fisher Kernels for Object Recognition",
BOOKTITLE = "ICCV",
YEAR = "2005",
PAGES = "I: 136-143",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat812.html#TT61973"