HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS		QUICK SEARCH:   [advanced] Author: Keyword(s): Year:  Vol:  Page:

This Article Full Text Full Text (PDF) Alert me when this article is cited Alert me if a correction is posted Services Similar articles in this journal Similar articles in PubMed Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via HighWire Citing Articles via Google Scholar Google Scholar Articles by Tenenbaum, J. B. Articles by Freeman, W. T. Search for Related Content PubMed PubMed Citation Articles by Tenenbaum, J. B. Articles by Freeman, W. T.

Separating Style and Content with Bilinear Models

Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology, Cambridge, MA 02139, U.S.A.

William T. Freeman

MERL, a Mitsubishi Electric Research Lab, 201 Broadway, Cambridge, MA 02139, U.S.A.

Correspondence: Current address: Department of Psychology, Stanford University, Stanford, CA 94305, U.S.A.

Perceptual systems routinely separate "content" from "style," classifying familiar words spoken in an unfamiliar accent, identifying a font or handwriting style across letters, or recognizing a familiar face or object seen under unfamiliar viewing conditions. Yet a general and tractable computational model of this ability to untangle the underlying factors of perceptual observations remains elusive (Hofstadter, 1985). Existing factor models (Mardia, Kent, & Bibby, 1979; Hinton & Zemel, 1994; Ghahramani, 1995; Bell & Sejnowski, 1995; Hinton, Dayan, Frey, & Neal, 1995; Dayan, Hinton, Neal, & Zemel, 1995; Hinton & Ghahramani, 1997) are either insufficiently rich to capture the complex interactions of perceptually meaningful factors such as phoneme and speaker accent or letter and font, or do not allow efficient learning algorithms. We present a general framework for learning to solve two-factor tasks using bilinear models, which provide sufficiently expressive representations of factor interactions but can nonetheless be fit to data using efficient algorithms based on the singular value decomposition and expectation-maximization. We report promising results on three different tasks in three different perceptual domains: spoken vowel classification with a benchmark multispeaker database, extrapolation of fonts to unseen letters, and translation of faces to novel illuminants.

This article has been cited by other articles:

				M. B. Ahrens, J. F. Linden, and M. Sahani Nonlinearities and Contextual Influences in Auditory Cortical Responses Modeled with Multilinear Spectrotemporal Methods J. Neurosci., February 20, 2008; 28(8): 1929 - 1942. [Abstract] [Full Text] [PDF]

				X. Miao and R. P. N. Rao Learning the Lie Groups of Visual Invariance Neural Comput., October 1, 2007; 19(10): 2665 - 2693. [Abstract] [Full Text] [PDF]

				R. Turner and M. Sahani A maximum-likelihood interpretation for slow feature analysis. Neural Comput., April 1, 2007; 19(4): 1022 - 1038. [Abstract] [Full Text] [PDF]

				P. Dayan Images, Frames, and Connectionist Hierarchies. Neural Comput., October 1, 2006; 18(10): 2293 - 2319. [Abstract] [Full Text] [PDF]

				B. A. Olshausen and D. J. Field How Close Are We to Understanding V1? Neural Comput., August 1, 2005; 17(8): 1665 - 1699. [Abstract] [Full Text] [PDF]

				D. B. Grimes and R. P. N. Rao Bilinear Sparse Coding for Invariant Vision Neural Comput., January 1, 2005; 17(1): 47 - 73. [Abstract] [Full Text] [PDF]