Object localisation using laterally connected "What" and "Where" associator networks

Authors:
Cornelius Weber;Stefan Wermter
Affiliations:
School of Computing and Technology, University of Sunderland, Sunderland, United Kingdom;School of Computing and Technology, University of Sunderland, Sunderland, United Kingdom
Venue:
ICANN/ICONIP'03 Proceedings of the 2003 joint international conference on Artificial neural networks and neural information processing
Year:
2003

Citing 3
Cited 3

Topographic receptive fields and patterned lateral interaction in a self-organizing model of the primary visual cortex

Neural Computation
Recurrent sampling models for the Helmholtz machine

Neural Computation
Bayesian Object Localisation in Images

International Journal of Computer Vision

A hybrid generative and predictive model of the motor cortex

Neural Networks
Image segmentation by complex-valued units

ICANN'05 Proceedings of the 15th international conference on Artificial Neural Networks: biological Inspirations - Volume Part I
A dynamic unsupervised laterally connected neural network architecture for integrative pattern discovery

ICONIP'11 Proceedings of the 18th international conference on Neural Information Processing - Volume Part II

Quantified Score

Hi-index	0.01

Visualization

Abstract

We describe an associator neural network to localise a recognised object within the visual field. The idea extends the use of lateral connections within a single cortical area to their use between different areas. Previously, intra-area lateral connections have been implemented within V1 to endow the simple cells with biologically realistic orientation tuning curves as well as to generate complex cell properties. In this paper we extend the lateral connections to also span an area laterally connected to the simulated V1. Their training was done by the following procedure: every image on the input contained an artificially generated orange fruit at a particular location. This location was reflected - in a supervised manner - as a Gaussian on the area laterally connected to V1. Thus, the lateral weights are trained to associate the V1 representation of the image to the location of the orange. After training, we present an image with an orange of which we do not know its location. By the means of pattern completion a Gaussian hill of activation emerges on the correct location of the laterally connected area. Tests display a good performance with real oranges under diverse lighting and backgrounds. A further extension to include multi-modal input is discussed.