Learning location invariance for object recognition and localization

Authors:
Gwendid T. van der Voort van der Kleij;Frank van der Velde;Marc de Kamps
Affiliations:
Cognitive Psychology Unit, University of Leiden, Leiden, The Netherlands;Cognitive Psychology Unit, University of Leiden, Leiden, The Netherlands;Robotics and Embedded Systems, Department of Informatics, Technische Universität München, Garching bei München, Germany
Venue:
BVAI'05 Proceedings of the First international conference on Brain, Vision, and Artificial Intelligence
Year:
2005

Citing 4
Cited 0

Representation of visual features of objects in the inferotemporal cortex

Neural Networks - 1996 Special issue: four major hypotheses in neuroscience
Neocognitron capable of incremental learning

Neural Networks
From Knowing What to Knowing Where: Modeling Object-Based Attention with Feedback Disinhibition of Activation

Journal of Cognitive Neuroscience
A neural model of binding and capacity in visual working memory

ICANN/ICONIP'03 Proceedings of the 2003 joint international conference on Artificial neural networks and neural information processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

A visual system not only needs to recognize a stimulus, it also needs to find the location of the stimulus. In this paper, we present a neural network model that is able to generalize its ability to identify objects to new locations in its visual field. The model consists of a feedforward network for object identification and a feedback network for object location. The feedforward network first learns to identify simple features at all locations and therefore becomes selective for location invariant features. This network subsequently learns to identify objects partly by learning new conjunctions of these location invariant features. Once the feedforward network is able to identify an object at a new location, all conditions for supervised learning of additional, location dependent features for the object are set. The learning in the feedforward network can be transferred to the feedback network, which is needed to localize an object at a new location.