A temporal stability approach to position and attention-shift-invariant recognition

Authors:
Muhua Li;James J. Clark
Affiliations:
Centre for Intelligent Machines, McGill University, Montréal, Québec, Canada H3A 2A7;Centre for Intelligent Machines, McGill University, Montréal, Québec, Canada H3A 2A7
Venue:
Neural Computation
Year:
2004

Citing 5
Cited 1

Learning invariance from transformation sequences

Neural Computation
A Model of Saliency-Based Visual Attention for Rapid Scene Analysis

IEEE Transactions on Pattern Analysis and Machine Intelligence
Implicit learning in 3D object recognition: the importance of temporal context

Neural Computation
Learning to Categorize Objects Using Temporal Coherence

Advances in Neural Information Processing Systems 5, [NIPS Conference]
Neurons with Two Sites of Synaptic Integration Learn Invariant Representations

Neural Computation

Selective Attention in the Learning of Viewpoint and Position Invariance

Attention in Cognitive Systems. Theories and Systems from an Interdisciplinary Viewpoint

Quantified Score

Hi-index	0.00

Visualization

Abstract

Incorporation of visual-related self-action signals can help neural networks learn invariance. We describe a method that can produce a network with invariance to changes in visual input caused by eye movements and covert attention shifts. Training of the network is controlled by signals associated with eye movements and covert attention shifting. A temporal perceptual stability constraint is used to drive the output of the network toward remaining constant across temporal sequences of saccadic motions and covert attention shifts. We use a four-layer neural network model to perform the position-invariant extraction of local features and temporal integration of invariant presentations of local features in a bottom-up structure. We present results on both simulated data and real images to demonstrate that our network can acquire both position and attention shift invariance.