Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/70329
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | An adversarial optimization approach to efficient outlier removal |
Author: | Yu, J. Eriksson, A. Chin, T. Suter, D. |
Citation: | 2011 IEEE International Conference on Computer Vision, 2011: pp.399-406 |
Publisher: | IEEE |
Publisher Place: | 345 E 47TH ST, NEW YORK, NY 10017 USA |
Issue Date: | 2011 |
Series/Report no.: | IEEE International Conference on Computer Vision |
ISBN: | 9781457711015 |
ISSN: | 1550-5499 |
Conference Name: | International Conference on Computer Vision (13th : 2011 : Barcelona, Spain) |
Statement of Responsibility: | Jin Yu, Anders Eriksson, Tat-Jun Chin, David Suter |
Abstract: | This paper proposes a novel adversarial optimization approach to efficient outlier removal in computer vision. We characterize the outlier removal problem as a game that involves two players of conflicting interests, namely, optimizer and outlier. Such an adversarial view not only brings new insights into various existing methods, but also gives rise to a general optimization framework that provably unifies them. Under the proposed framework, we develop a new outlier removal approach that is able to offer a much needed control over the trade-off between reliability and speed, which is otherwise not available in previous methods. The proposed approach is driven by a mixed-integer minmax (convex-concave) optimization process. Although a minmax problem is generally not amenable to efficient optimization, we show that for some commonly used vision objective functions, an equivalent Linear Program reformulation exists. We demonstrate our method on two representative multiview geometry problems. Experiments on real image data illustrate superior practical performance of our method over recent techniques. |
Rights: | Copyright © 2011 by IEEE. |
DOI: | 10.1109/ICCV.2011.6126268 |
Description (link): | http://www.iccv2011.org/ |
Published version: | http://www.iccv2011.org/authors/accepted-papers |
Appears in Collections: | Aurora harvest 5 Computer Science publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
RA_hdl_70329.pdf | Restricted Access | 4.02 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.