Informatics Report Series


Report   

EDI-INF-RR-0259


Related Pages

Report (by Number) Index
Report (by Date) Index
Author Index
Institute Index

Home
Title:Greedy Learning of Multiple Objects in Images using Robust Statistics and Factorial Learning
Authors: Chris Williams ; Michalis Titsias
Date:May 2004
Publication Title:Neural Computation
Publisher:MIT Press
Publication Type:Journal Article Publication Status:Published
Volume No:16(5) Page Nos:1039-1062
DOI:10.1162/089976604773135096
Abstract:
We consider data which are images containing views of multiple objects. Our task is to learn about each of the objects present in the images. This task can be approached as a factorial learning problem, where each image must be explained by instantiating a model for each of the objects present with the correct instantiation parameters. A major problem with learning a factorial model is that as the number of objects increases, there is a combinatorial explosion of the number of configurations that need to be considered. We develop a method to extract object models sequentially from the data by making use of a robust statistical method, thus avoiding the combinatorial explosion, and present results showing successful extraction of objects from real images.
Links To Paper
1st link
Bibtex format
@Article{EDI-INF-RR-0259,
author = { Chris Williams and Michalis Titsias },
title = {Greedy Learning of Multiple Objects in Images using Robust Statistics and Factorial Learning},
journal = {Neural Computation},
publisher = {MIT Press},
year = 2004,
month = {May},
volume = {16(5)},
pages = {1039-1062},
doi = {10.1162/089976604773135096},
url = {http://homepages.inf.ed.ac.uk/ckiw/papers/lmo8.pdf},
}


Home : Publications : Report 

Please mail <reports@inf.ed.ac.uk> with any changes or corrections.
Unless explicitly stated otherwise, all material is copyright The University of Edinburgh