Edinburgh Research Explorer

Comparison of Generative and Discriminative Techniques for Object Detection and Classification

Research output: Chapter in Book/Report/Conference proceedingChapter (peer-reviewed)

Original languageEnglish
Title of host publicationToward Category-Level Object Recognition
EditorsJean Ponce, Martial Hebert, Cordelia Schmid, Andrew Zisserman
PublisherSpringer Berlin Heidelberg
Pages173-195
Number of pages23
ISBN (Electronic)978-3-540-68795-5
ISBN (Print)978-3-540-68794-8
DOIs
Publication statusPublished - 2006

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Berlin Heidelberg
Volume4170
ISSN (Print)0302-9743

Abstract

Many approaches to object recognition are founded on probability theory, and can be broadly characterized as either generative or discriminative according to whether or not the distribution of the image features is modelled. Generative and discriminative methods have very different characteristics, as well as complementary strengths and weaknesses. In this chapter we introduce new generative and discriminative models for object detection and classification based on weakly labelled training data. We use these models to illustrate the relative merits of the two approaches in the context of a data set of widely varying images of non-rigid objects (animals). Our results support the assertion that neither approach alone will be sufficient for large scale object recognition, and we discuss techniques for combining the strengths of generative and discriminative approaches.

ID: 22928677