Incremental Figure-Ground Segmentation Using Localized Adaptive Metrics in LVQ

Authors:
Alexander Denecke;Heiko Wersing;Jochen J. Steil;Edgar Körner
Affiliations:
Bielefeld University - CoR-Lab, Bielefeld, Germany D-33501 and Honda Research Institute Europe, Offenbach/Main, Germany D-63073;Honda Research Institute Europe, Offenbach/Main, Germany D-63073;Bielefeld University - CoR-Lab, Bielefeld, Germany D-33501;Honda Research Institute Europe, Offenbach/Main, Germany D-63073
Venue:
WSOM '09 Proceedings of the 7th International Workshop on Advances in Self-Organizing Maps
Year:
2009

Citing 6
Cited 0

Life-long learning cell structures —continuously learning without catastrophic interference

Neural Networks
The LBG-U Method for Vector Quantization – an Improvement over LBGInspired from Neural Networks

Neural Processing Letters
Margin-based active learning for LVQ networks

Neurocomputing
A biologically motivated visual memory architecture for online learning of objects

Neural Networks
A supervised growing neural gas algorithm for cluster analysis

International Journal of Hybrid Intelligent Systems
Online figure-ground segmentation with adaptive metrics in generalized LVQ

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Vector quantization methods are confronted with a model selection problem, namely the number of prototypical feature representatives to model each class. In this paper we present an incremental learning scheme in the context of figure-ground segmentation. In presence of local adaptive metrics and supervised noisy information we use a parallel evaluation scheme combined with a local utility function to organize a learning vector quantization (LVQ) network with an adaptive number of prototypes and verify the capabilities on a real world figure-ground segmentation task.