CaltechAUTHORS
  A Caltech Library Service

A Discriminative Framework for Modelling Object Classes

Holub, Alex and Perona, Pietro (2005) A Discriminative Framework for Modelling Object Classes. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE , Los Alamitos, CA, pp. 664-671. ISBN 0-7695-2372-2 http://resolver.caltech.edu/CaltechAUTHORS:20110809-084835731

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

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20110809-084835731

Abstract

Here we explore a discriminative learning method on underlying generative models for the purpose of discriminating between object categories. Visual recognition algorithms learn models from a set of training examples. Generative models learn their representations by considering data from a single class. Generative models are popular in computer vision for many reasons, including their ability to elegantly incorporate prior knowledge and to handle correspondences between object parts and detected features. However, generative models are often inferior to discriminative models during classification tasks. We study a discriminative approach to learning object categories which maintains the representational power of generative learning, but trains the generative models in a discriminative manner. The discriminatively trained models perform better during classification tasks as a result of selecting discriminative sets of features. We conclude by proposing a multiclass object recognition system which initially trains object classes in a generative manner, identifies subsets of similar classes with high confusion, and finally trains models for these subsets in a discriminative manner to realize gains in classification performance.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
http://dx.doi.org/10.1109/CVPR.2005.25DOIUNSPECIFIED
http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1467332PublisherUNSPECIFIED
Additional Information:© 2005 IEEE. Issue Date: 20-25 June 2005. Date of Current Version: 25 July 2005. C. Rasmussen for making the conjugate gradient code ’minimize’ publicly available and L. Zelnik, R. Fergus, F.F. Li, and G. Hinton for useful discussions.
Other Numbering System:
Other Numbering System NameOther Numbering System ID
INSPEC Accession Number8588926
Record Number:CaltechAUTHORS:20110809-084835731
Persistent URL:http://resolver.caltech.edu/CaltechAUTHORS:20110809-084835731
Official Citation:Holub, A.; Perona, P.; , "A discriminative framework for modelling object classes," Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on , vol.1, no., pp. 664- 671 vol. 1, 20-25 June 2005 doi: 10.1109/CVPR.2005.25 URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=1467332&isnumber=31472
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:24751
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:12 Sep 2011 16:13
Last Modified:12 Sep 2011 16:13

Repository Staff Only: item control page