Perception strategies in hierarchical vision systems

Lior Wolf*, Stan Bileschi, Ethan Meyers

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Flat appearance-based systems, which combine clever image representations with standard classifiers, might be the most effective way to recognize objects using current technologies. In the future, however, it seems probable that hierarchical representations might have better performance. In such systems, the image representation consists of a sequence of sets of features, where each subsequent set is computed based on the previous sets. The main contributions of this paper are to: (1) pose the question "what is the best way to employ discriminative methods for hierarchical image representations?"; (2) enumerate some of the alternative hierarchies while drawing connections to recent work by brain researchers; (3) study experimentally the different alternatives. As we will show, the strategy used can make a substantial difference.

Original languageEnglish
Title of host publicationProceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006
Pages2153-2160
Number of pages8
DOIs
StatePublished - 2006
Externally publishedYes
Event2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006 - New York, NY, United States
Duration: 17 Jun 200622 Jun 2006

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume2
ISSN (Print)1063-6919

Conference

Conference2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006
Country/TerritoryUnited States
CityNew York, NY
Period17/06/0622/06/06

Fingerprint

Dive into the research topics of 'Perception strategies in hierarchical vision systems'. Together they form a unique fingerprint.

Cite this