Learning of Position-Invariant Object Representation Across Attention Shifts

• Published in: Attention and Performance in Computational Vision pp. 57 - 70
• Main Authors: Li, Muhua, Clark, James J.
• Format: Book Chapter Conference Proceeding
• Language: English
• Published: Berlin, Heidelberg Springer Berlin Heidelberg 2005; Springer
• Series: Lecture Notes in Computer Science
• Subjects: Applied sciences; Artificial intelligence; Computer science; control theory; systems; Exact sciences and technology; Hide Layer; Learning Rule; Local Feature; Neural Response; Pattern recognition. Digital image processing. Computational geometry; Retinal Image; Selective attention; Invariant; Computer vision; Image processing; Image databank; Feature extraction; Invariance; Pattern recognition; Neural network; Visual attention; Temporal constraint; Pattern extraction
• ISBN: 9783540244219; 3540244212
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-540-30572-9_5

Selective attention shift can help neural networks learn invariance. We describe a method that can produce a network with invariance to changes in visual input caused by attention shifts. Training of the network is controlled by signals associated with attention shifting. A temporal perceptual stability constraint is used to drive the output of the network towards remaining constant across temporal sequences of attention shifts. We use a four-layer neural network model to perform the position-invariant extraction of local features and temporal integration of attention-shift invariant presentations of objects. We present results on both simulated data and real images, to demonstrate that our network can acquire position invariance across a sequence of attention shifts.