Summary: An integrated network for invariant visual detection and recognition
Yali Amit a,*, Massimo Mascaro b
Department of Statistics, University of Chicago, Chicago, IL 60637, USA
Dipartimento di Fisiologia Umana e Farmacologia, Universita di Roma, La Sapienza, Rome, Italy
Received 5 June 2002; received in revised form 5 December 2002
We describe an architecture for invariant visual detection and recognition. Learning is performed in a single central module. The
architecture makes use of a replica module consisting of copies of retinotopic layers of local features, with a particular design of
inputs and outputs, that allows them to be primed either to attend to a particular location, or to attend to a particular object
representation. In the former case the data at a selected location can be classified in the central module. In the latter case all instances
of the selected object are detected in the field of view. The architecture is used to explain a number of psychophysical and physi-
ological observations: object based attention, the different response time slopes of target detection among distractors, and observed
attentional modulation of neuronal responses. We hypothesize that the organization of visual cortex in columns of neurons re-
sponding to the same feature at the same location may provide the copying architecture needed for translation invariance.
Ó 2003 Elsevier Ltd. All rights reserved.
Keywords: Invariance; Attention; Object detection; Object recognition; Hebbian learning
The visual system performs complex detection and