Deep Lambertian Networks

Visual perception is a challenging problem in part due to illumination variations. A possible solution is to first estimate an illumination invariant representation before using it for recognition. The object albedo and surface normals are examples of such representations. In this paper, we introduce a multilayer generative model where the latent variables include the albedo, surface normals, and the light source. Combining Deep Belief Nets with the Lambertian reectance assumption, our model can learn good priors over the albedo from 2D images. Illumination variations can be explained by changing only the lighting latent variable in our model. By transferring learned knowledge from similar objects, albedo and surface normals estimation from a single image is possible in our model. Experiments demonstrate that our model is able to generalize as well as improve over standard baselines in one-shot face recognition.

[1]  H. Barrow,et al.  RECOVERING INTRINSIC SCENE CHARACTERISTICS FROM IMAGES , 1978 .

[2]  Robert J. Woodham,et al.  Photometric method for determining surface orientation from multiple images , 1980 .

[3]  S. Duane,et al.  Hybrid Monte Carlo , 1987 .

[4]  V. Ramachandran,et al.  On the perception of shape from shading , 1988, Nature.

[5]  V. S. Ramachandran,et al.  Perception of shape from shading , 1988, Nature.

[6]  Hideki Hayakawa.  Photometric stereo under a light source with arbitrary motion , 1994 .

[7]  David J. Kriegman,et al.  What is the set of images of an object under all possible lighting conditions? , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[8]  Geoffrey E. Hinton,et al.  A View of the Em Algorithm that Justifies Incremental, Sparse, and other Variants , 1998, Learning in Graphical Models.

[9]  Matthew Turk,et al.  A Morphable Model For The Synthesis Of 3D Faces , 1999, SIGGRAPH.

[10]  Thomas Vetter,et al.  A morphable model for the synthesis of 3D faces , 1999, SIGGRAPH.

[11]  David J. Kriegman,et al.  From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Geoffrey E. Hinton.  Training Products of Experts by Minimizing Contrastive Divergence , 2002, Neural Computation.

[13]  Daniel Snow,et al.  Determining Generative Models of Objects Under Varying Illumination: Shape and Albedo from Multiple Images Using SVD and Integrability , 1999, International Journal of Computer Vision.

[14]  Arnold W. M. Smeulders,et al.  The Amsterdam Library of Object Images , 2004, International Journal of Computer Vision.

[15]  David J. Kriegman,et al.  Acquiring linear subspaces for face recognition under variable lighting , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[17]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[18]  Lei Zhang,et al.  Face recognition from a single training image under arbitrary unknown lighting using spherical harmonics , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Honglak Lee,et al.  Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations , 2009, ICML '09.

[20]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[21]  Gang Hua,et al.  Face Relighting from a Single Image under Arbitrary Unknown Lighting Conditions , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Quoc V. Le,et al.  Tiled convolutional neural networks , 2010, NIPS.

[23]  Yann LeCun,et al.  Convolutional Learning of Spatio-temporal Features , 2010, ECCV.

[24]  Bernt Schiele,et al.  Disparity statistics for pedestrian detection: combining appearance, motion and stereo , 2010, ECCV 2010.

[25]  Geoffrey E. Hinton,et al.  Modeling pixel means and covariances using factorized third-order boltzmann machines , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[26]  Peter V. Gehler,et al.  Recovering Intrinsic Images with a Global Sparsity Prior on Reflectance , 2011, NIPS.

[27]  Radford M. Neal.  MCMC Using Hamiltonian Dynamics , 2011, 1206.1901.

[28]  Geoffrey E. Hinton,et al.  Acoustic Modeling Using Deep Belief Networks , 2012, IEEE Transactions on Audio, Speech, and Language Processing.