Face Representation in Cortex: Studies Using a Simple and Not So Special Model
Item
-
Title
-
en_US
Face Representation in Cortex: Studies Using a Simple and Not So Special Model
-
Creator
-
en_US
Rosen, Ezra
-
Date
-
2004-10-01T14:00:11Z
-
Date Available
-
2004-10-01T14:00:11Z
-
Date Issued
-
en_US
2003-06-05
-
Identifier
-
en_US
AITR-2003-010
-
en_US
CBCL-228
-
Abstract
-
en_US
The face inversion effect has been widely documented as an effect of the uniqueness of face processing. Using a computational model, we show that the face inversion effect is a byproduct of expertise with respect to the face object class. In simulations using HMAX, a hierarchical, shape based model, we show that the magnitude of the inversion effect is a function of the specificity of the representation. Using many, sharply tuned units, an ``expert'' has a large inversion effect. On the other hand, if fewer, broadly tuned units are used, the expertise is lost, and this ``novice'' has a small inversion effect. As the size of the inversion effect is a product of the representation, not the object class, given the right training we can create experts and novices in any object class. Using the same representations as with faces, we create experts and novices for cars. We also measure the feasibility of a view-based model for recognition of rotated objects using HMAX. Using faces, we show that transfer of learning to novel views is possible. Given only one training view, the view-based model can recognize a face at a new orientation via interpolation from the views to which it had been tuned. Although the model can generalize well to upright faces, inverted faces yield poor performance because the features change differently under rotation.
-
Extent
-
en_US
66 p.
-
13121869 bytes
-
3182779 bytes
-
Format
-
application/postscript
-
application/pdf
-
Language
-
en_US
-
Relation
-
en_US
AITR-2003-010
-
en_US
CBCL-228
-
Subject
-
en_US
AI
-
en_US
Face Recognition
-
en_US
Representation
-
en_US
Invariance
-
en_US
HMAX