A Caltech Library Service

Hybrid generative-discriminative visual categorization

Holub, Alex D. and Welling, Max and Perona, Pietro (2008) Hybrid generative-discriminative visual categorization. International Journal of Computer Vision, 77 (1-3). pp. 239-258. ISSN 0920-5691. doi:10.1007/s11263-007-0084-6.

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item:


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' (Jaakola, T., et al. in Advances in neural information processing systems, Vol. 11, pp. 487-493, 1999), 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 unlabeled data.

Item Type:Article
Related URLs:
URLURL TypeDescription ReadCube access
Perona, Pietro0000-0002-7583-5809
Additional Information:© Springer Science+Business Media, LLC 2007. Received: 14 September 2005 / Accepted: 15 August 2007 / Published online: 18 October 2007.
Subject Keywords:Machine learning; Object recognition; Discriminative learning; Support vector machines
Issue or Number:1-3
Record Number:CaltechAUTHORS:20140730-101716299
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:47591
Deposited By: Caroline Murphy
Deposited On:22 Aug 2014 19:45
Last Modified:10 Nov 2021 17:48

Repository Staff Only: item control page