A neuro-dynamic architecture for one shot learning of objects that uses both bottom-up recognition and top-down prediction

Authors:
Christian Faubel;Gregor Schöner
Affiliations:
Gregor Schöner are with Institut f ür Neuroinformatik, Ruhr-Universität Bochum, Bochum, Germany;Gregor Schöner are with Institut f ür Neuroinformatik, Ruhr-Universität Bochum, Bochum, Germany
Venue:
IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Year:
2009

Citing 8
Cited 1

The Design and Use of Steerable Filters

IEEE Transactions on Pattern Analysis and Machine Intelligence
Color indexing

International Journal of Computer Vision
SEEMORE: combining color, shape, and texture histogramming in a neurally inspired approach to visual object recognition

Neural Computation
Map-Seeking Circuits in Visual Cognition: A Computational Mechanism for Biological and Machine Vision

Map-Seeking Circuits in Visual Cognition: A Computational Mechanism for Biological and Machine Vision
Learning optimized features for hierarchical models of invariant object recognition

Neural Computation
A Bayesian Approach to Unsupervised One-Shot Learning of Object Categories

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Object Recognition with Features Inspired by Visual Cortex

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
2008 Special Issue: Learning to recognize objects on the fly: A neurally based dynamic field approach

Neural Networks

A multifactor winner-take-all dynamics

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Learning to recognize objects from a small number of example views is a difficult problem of robot vision, of particular importance to assistance robots who are taught by human users. Here we present an approach that combines bottom-up recognition of matching patterns and top-down estimation of pose parameters in a recurrent loop that improves on previous efforts to reconcile invariance of recognition under view changes with discrimination among different objects. We demonstrate and evaluate the approach both in a service robotics implementation as well as on the COIL database. The robotic implementation highlights features of our approach that enable real-time pose tracking as well as recognition from views where figure ground segmentation is difficult.