Learning of Position-Invariant Object Representation Across Attention Shifts

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.