Robust Boltzmann Machines for recognition and denoising

While Boltzmann Machines have been successful at unsupervised learning and density modeling of images and speech data, they can be very sensitive to noise in the data. In this paper, we introduce a novel model, the Robust Boltzmann Machine (RoBM), which allows Boltzmann Machines to be robust to corruptions. In the domain of visual recognition, the RoBM is able to accurately deal with occlusions and noise by using multiplicative gating to induce a scale mixture of Gaussians over pixels. Image denoising and in-painting correspond to posterior inference in the RoBM. Our model is trained in an unsupervised fashion with unlabeled noisy data and can learn the spatial structure of the occluders. Compared to standard algorithms, the RoBM is significantly better at recognition and denoising on several face databases.

[1]  Peter J. Huber,et al.  Robust Statistics , 2005, Wiley Series in Probability and Statistics.

[2]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Paul Smolensky,et al.  Information processing in dynamical systems: foundations of harmony theory , 1986 .

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

[5]  David J. Kriegman,et al.  The yale face database , 1997 .

[6]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[7]  Aleix M. Martinez,et al.  The AR face database , 1998 .

[8]  L. Younes.  On the convergence of markovian stochastic algorithms with rapidly decreasing ergodicity rates , 1999 .

[9]  Konstantinos N. Plataniotis,et al.  Face recognition using kernel direct discriminant analysis algorithms , 2003, IEEE Trans. Neural Networks.

[10]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[11]  Christopher K. I. Williams,et al.  Greedy Learning of Multiple Objects in Images Using Robust Statistics and Factorial Learning , 2004, Neural Computation.

[12]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[13]  Christopher M. Bishop,et al.  Robust Bayesian Mixture Modelling , 2005, ESANN.

[14]  P. Rousseeuw,et al.  Wiley Series in Probability and Mathematical Statistics , 2005 .

[15]  Michael J. Black,et al.  Fields of Experts: a framework for learning image priors , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[16]  Brendan J. Frey,et al.  Generative Model for Layers of Appearance and Deformation , 2005, AISTATS.

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

[18]  Aleix M. Martínez,et al.  Face recognition with occlusions in the training and testing sets , 2008, 2008 8th IEEE International Conference on Automatic Face & Gesture Recognition.

[19]  Tijmen Tieleman,et al.  Training restricted Boltzmann machines using approximations to the likelihood gradient , 2008, ICML '08.

[20]  Geoffrey E. Hinton,et al.  Using fast weights to improve persistent contrastive divergence , 2009, ICML '09.

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

[22]  Hossein Mobahi,et al.  Face recognition with contiguous occlusion using markov random fields , 2009, 2009 IEEE 12th International Conference on Computer Vision.

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

[24]  Allen Y. Yang,et al.  Robust Face Recognition via Sparse Representation , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[26]  Gated Boltzmann Machine for Recognition under Occlusion , 2010 .

[27]  Nicolas Le Roux,et al.  Weakly Supervised Learning of Foreground-Background Segmentation Using Masked RBMs , 2011, ICANN.

[28]  Nicolas Le Roux,et al.  Learning a Generative Model of Images by Factoring Appearance and Shape , 2011, Neural Computation.

[29]  Geoffrey E. Hinton,et al.  On deep generative models with applications to recognition , 2011, CVPR 2011.

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