Learning Viewpoint Invariant Representations of Faces in anAttractor

In natural visual experience, diierent views of an object tend to appear in close temporal proximity as an animal manipulates the object or navigates around it. We investigated the ability of an attractor network to acquire view invariant visual representations by associating rst neighbors in a pattern sequence. The pattern sequence contains successive views of faces of ten individuals as they change pose. Under the network dynamics developed by Griniasty, Tsodyks & Amit (1993), multiple views of a given subject fall into the same basin of attraction. We use an independent component (ICA) representation of the faces for the input patterns (Bell & Sejnowski, 1995). The ICA representation has advantages over the principal component representation (PCA) for viewpoint-invariant recognition both with and without the attractor network, suggesting that ICA is a better representation than PCA for object recognition.

[1]  Terrence J. Sejnowski,et al.  An Information-Maximization Approach to Blind Separation and Blind Deconvolution , 1995, Neural Computation.

[2]  E. Rolls.  Learning mechanisms in the temporal lobe visual cortex , 1995, Behavioural Brain Research.

[3]  D. Amit.  The Hebbian paradigm reintegrated: Local reverberations as internal representations , 1995, Behavioral and Brain Sciences.

[4]  Peter Földiák,et al.  Learning Invariance from Transformation Sequences , 1991, Neural Comput..

[5]  Daniel J. Amit,et al.  Conversion of Temporal Correlations Between Stimuli to Spatial Correlations Between Attractors , 1999, Neural Computation.

[6]  Low-dimensional representations of Aut (F2) , 1996 .

[7]  Mark H. Johnson,et al.  Object Recognition and Sensitive Periods: A Computational Analysis of Visual Imprinting , 1994, Neural Computation.

[8]  Y. Miyashita.  Neuronal correlate of visual associative long-term memory in the primate temporal cortex , 1988, Nature.

[9]  David Beymer,et al.  Face recognition under varying pose , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[10]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[11]  Alice J. O'Toole,et al.  Low-dimensional representation of faces in higher dimensions of the face space , 1993 .

[12]  Terrence J. Sejnowski,et al.  The “independent components” of natural scenes are edge filters , 1997, Vision Research.

[13]  Terrence J. Sejnowski,et al.  Unsupervised Learning Of Invariant Representations Of Faces Through Temporal Association , 1996 .

[14]  M. Stryker.  Temporal associations , 1991, Nature.