Back to search

University of British Columbia

Bayesian formulations of multiple instance learning with applications to general object recognition

Abstract

dc:description

We attack the problem of general object recognition by learning probabilistic, nonlinear object classifiers for a large number of object classes. The individual classifiers allow for detection and localization of objects belonging to a certain class in an image by classifying image regions into those that likely show such an object and those that do not. Instead of relying on expensive supervised training data, we propose an approach for learning such classifiers from annotated images. One major problem to overcome in this scenario is the ambiguity due to the unknown associations between annotation words and image regions. We propose a fully Bayesian learning technique for learning probabilistic classifiers, which deals with the ambiguity issue in a principled way by integrating out the uncertainty in both the unknown associations and the parameters of our probabilistic model. Our approach uses an extremely flexible kernel classifier trained with an efficient Markov Chain Monte Carlo technique. A further problem in this setting is that of class imbalance, which we address in two different ways. Firstly, we propose a new problem formulation, in which we provide our training algorithm with additional information, namely estimates of the number of image regions showing the object class in the given training images. Additionally, we experiment with altering the distribution of the training data itself. Using only an automatic and appropriately chosen subset of the available training images without the object class of interest leads to a more balanced class distribution as well as a remarkable speedup in training and testing. The value of the new techniques is demonstrated in synthetic and real image datasets.

Degree

thesis:*
Name thesis:degree_name
Master of Science - MSc
Level thesis:degree_level
master's
Discipline thesis:degree_discipline
Computer Science
Grantor dc:publisher
University of British Columbia
Year dc:date
2004

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Kück, Hendrik

Rights

dc:rights
Statement dc:rights
  • For non-commercial purposes only, such as research, private study and education. Additional conditions apply, see Terms of Use https://open.library.ubc.ca/terms_of_use.
Language dc:language
eng

Identifiers

dc:identifier.*
Handle dc:identifier
http://hdl.handle.net/2429/15680

Chain of custody

source
Harvested from
University of British Columbia
Base URL
circle.library.ubc.ca/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
related terms
citation

Kück, Hendrik. Bayesian formulations of multiple instance learning with applications to general object recognition. master's thesis, University of British Columbia, 2004. http://hdl.handle.net/2429/15680