Hybrid Generative-Discriminative Visual Categorization

Authors:
Alex D. Holub;Max Welling;Pietro Perona
Affiliations:
Computation and Neural Systems, California Institute of Technology, Pasadena, USA 91125;Department of Computer Science, University of California Irvine, Irvine, USA 92697-3425;Computation and Neural Systems, California Institute of Technology, Pasadena, USA 91125
Venue:
International Journal of Computer Vision
Year:
2008

Citing 12
Cited 5

Exploiting generative models in discriminative classifiers

Proceedings of the 1998 conference on Advances in neural information processing systems II
Saliency, Scale and Image Description

International Journal of Computer Vision
Choosing Multiple Parameters for Support Vector Machines

Machine Learning
Recognition of Planar Object Classes

CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
Recognition with Local Features: the Kernel Recipe

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Kernel Methods for Pattern Analysis

Kernel Methods for Pattern Analysis
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories

CVPRW '04 Proceedings of the 2004 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'04) Volume 12 - Volume 12
A Discriminative Framework for Modelling Object Classes

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Combining Generative Models and Fisher Kernels for Object Recognition

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
2005 Special Issue: Bayesian approach to feature selection and parameter tuning for support vector machine classifiers

Neural Networks - 2005 Special issue: IJCNN 2005
Learning a restricted Bayesian network for object detection

CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition

A hybrid generative/discriminative framework to train a semantic parser from an un-annotated corpus

COLING '08 Proceedings of the 22nd International Conference on Computational Linguistics - Volume 1
Context-based multi-label image annotation

Proceedings of the ACM International Conference on Image and Video Retrieval
Learning Visual Object Categories for Robot Affordance Prediction

International Journal of Robotics Research
Bayesian hybrid generative discriminative learning based on finite Liouville mixture models

Pattern Recognition
Deriving kernels from generalized Dirichlet mixture models and applications

Information Processing and Management: an International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.