Selective Attention in the Learning of Viewpoint and Position Invariance

Authors:
Muhua Li;James J. Clark
Affiliations:
Centre for Intelligent Machines, McGill University,;Centre for Intelligent Machines, McGill University,
Venue:
Attention in Cognitive Systems. Theories and Systems from an Interdisciplinary Viewpoint
Year:
2008

Citing 5
Cited 0

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
View-Based Dynamic Object Recognition Based on Human Perception

ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 3 - Volume 3
A temporal stability approach to position and attention-shift-invariant recognition

Neural Computation
Learning of position-invariant object representation across attention shifts

WAPCV'04 Proceedings of the Second international conference on Attention and Performance in Computational Vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

Selective attention plays an important role in visual processing in reducing the problem scale and in actively gathering useful information. We propose a modified saliency map mechanism that uses a simple top-down task-dependent cue to allow attention to stay mainly on one object in the scene each time for the first few shifts. Such a method allows the learning of invariant object representations across attention shifts in a multiple-object scene. In this paper, we construct a neural network that can learn position and viewpoint invariant representations for objects across attention shifts in a temporal sequence.