Manifold Based Face Synthesis from Sparse Samples

Data sparsity has been a thorny issue for manifold-based image synthesis, and in this paper we address this critical problem by leveraging ideas from transfer learning. Specifically, we propose methods based on generating auxiliary data in the form of synthetic samples using transformations of the original sparse samples. To incorporate the auxiliary data, we propose a weighted data synthesis method, which adaptively selects from the generated samples for inclusion during the manifold learning process via a weighted iterative algorithm. To demonstrate the feasibility of the proposed method, we apply it to the problem of face image synthesis from sparse samples. Compared with existing methods, the proposed method shows encouraging results with good performance improvements.

[1]  Narendra Ahuja,et al.  Dynamic Textures Synthesis as Nonlinear Manifold Learning and Traversing , 2006, BMVC.

[2]  Peter Stone,et al.  Transfer Learning for Reinforcement Learning Domains: A Survey , 2009, J. Mach. Learn. Res..

[3]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[4]  Stephen M. Omohundro,et al.  Nonlinear Image Interpolation using Manifold Learning , 1994, NIPS.

[5]  Rui Li,et al.  Simultaneous Learning of Nonlinear Manifold and Dynamical Models for High-dimensional Time Series , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[6]  张振跃,et al.  Principal Manifolds and Nonlinear Dimensionality Reduction via Tangent Space Alignment , 2004 .

[7]  Lei Zhang,et al.  Face synthesis and recognition from a single image under arbitrary unknown lighting using a spherical harmonic basis morphable model , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[8]  V. Pavlovic,et al.  Regression using Gaussian Process manifold kernel dimensionality reduction , 2008, 2008 IEEE Workshop on Machine Learning for Signal Processing.

[9]  René Vidal,et al.  Sparse Manifold Clustering and Embedding , 2011, NIPS.

[10]  Joshua B. Tenenbaum,et al.  Learning to share visual appearance for multiclass object detection , 2011, CVPR 2011.

[11]  Serge J. Belongie,et al.  Learning to Traverse Image Manifolds , 2006, NIPS.

[12]  Matti Pietikäinen,et al.  Learning mappings for face synthesis from near infrared to visual light images , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  J. Crowley,et al.  Estimating Face orientation from Robust Detection of Salient Facial Structures , 2004 .

[14]  Neil D. Lawrence,et al.  Dataset Shift in Machine Learning , 2009 .

[15]  Miguel Á. Carreira-Perpiñán,et al.  Manifold Learning and Missing Data Recovery through Unsupervised Regression , 2011, 2011 IEEE 11th International Conference on Data Mining.

[16]  Antonio Torralba,et al.  Transfer Learning by Borrowing Examples for Multiclass Object Detection , 2011, NIPS.

[17]  Ahmed M. Elgammal,et al.  Modeling View and Posture Manifolds for Tracking , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[18]  P. Thomas Fletcher,et al.  Polynomial Regression on Riemannian Manifolds , 2012, ECCV.

[19]  Jun Wang,et al.  Reconstruction and analysis of multi-pose face images based on nonlinear dimensionality reduction , 2004, Pattern Recognit..

[20]  Andrés Marino Álvarez-Meza,et al.  Image Synthesis Based on Manifold Learning , 2011, CAIP.

[21]  Ahmed M. Elgammal,et al.  Regression from local features for viewpoint and pose estimation , 2011, 2011 International Conference on Computer Vision.

[22]  Zhang Yi,et al.  Manifold-Based Learning and Synthesis , 2009, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[23]  Hongyuan Zha,et al.  Adaptive Manifold Learning , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.