iccv iccv2013 iccv2013-259 iccv2013-259-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Hongteng Xu, Hongyuan Zha
Abstract: Data sparsity has been a thorny issuefor 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] A. M. A´lvarez-Meza, J. Valencia-Aguirre, G. DazaSantacoloma, C. D. Acosta-Medina, and G. CastellanosDom ı´nguez. Image synthesis based on manifold learning. In Computer Analysis of Images and Patterns, pages 405–412. Springer, 2011. 1
[2] C. Bregler and S. M. Omohundro. Nonlinear image interpolation using manifold learning. Advances in neural informa-
[3]
[4]
[5]
[6]
[7]
[8]
[9]
[10]
[11] tion processing systems, pages 973–980, 1995. 1 M. A. Carreira-Perpin a´n and Z. Lu. Manifold learning and missing data recovery through unsupervised regression. In ICDM, pages 1014–1019. IEEE, 2011. 1 J. Chen, D. Yi, J. Yang, G. Zhao, S. Z. Li, and M. Pietikainen. Learning mappings for face synthesis from near infrared to visual light images. In CVPR, pages 156–163. IEEE, 2009. 1, 2 P. Doll a´r, V. Rabaud, and S. Belongie. Learning to traverse image manifolds. Advances in neural informationprocessing systems, 19:361, 2007. 1, 2, 6, 7, 8 E. Elhamifar and R. Vidal. Sparse manifold clustering and embedding. Advances in Neural Information Processing Systems, 24:55–63, 2011. 4 N. Gourier, D. Hall, and J. L. Crowley. Estimating face orientation from robust detection of salient facial structures. In FG Net Workshop on Visual Observation ofDeictic Gestures, pages 1–9, 2004. 5 J. Hinkle, P. Muralidharan, P. T. Fletcher, and S. Joshi. Polynomial regression on riemannian manifolds. In ECCV, pages 1–14. Springer, 2012. 3 D. Huang, Z. Yi, and X. Pu. Manifold-based learning and synthesis. Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on, 39(3):592–606, 2009. 1, 6, 7, 8 C.-S. Lee and A. Elgammal. Modeling view and posture manifolds for tracking. In ICCV, pages 1–8. IEEE, 2007. 1 R. Li, T.-P. Tian, and S. Sclaroff. Simultaneous learning of nonlinear manifold and dynamical models for highdimensional time series. In ICCV, pages 1–8. IEEE, 2007. 1
[12] J. J. Lim, R. Salakhutdinov, and A. Torralba. Transfer learning by borrowing examples for multiclass object detection. In NIPS, 2011. 2, 3
[13] C.-B. Liu, R.-S. Lin, N. Ahuja, and M. Yang. Dynamic textures synthesis as nonlinear manifold learning and traversing. In BMVC, volume 2, pages 859–868. Citeseer, 2006. 1
[14] K. Moon and V. Pavlovic. Regression using gaussian process manifold kernel dimensionality reduction. In MLSP, pages 14–19. IEEE, 2008. 1
[15] S. J. Pan and Q. Yang. A survey on transfer learning. Knowledge and Data Engineering, IEEE Transactions on, 22(10): 1345–1359, 2010. 2
[16] J. Quionero-Candela, M. Sugiyama, A. Schwaighofer, and N. D. Lawrence. Dataset shift in machine learning. The MIT Press, 2009. 2
[17] R. Salakhutdinov, A. Torralba, and J. Tenenbaum. Learning to share visual appearance for multiclass object detection. In CVPR, pages 1481–1488. IEEE, 2011. 2
[18] M. E. Taylor and P. Stone. Transfer learning for reinforcement learning domains: A survey. The Journal of Machine Learning Research, 10: 1633–1685, 2009. 2
[19] M. Torki and A. Elgammal. Regression from local features for viewpoint and pose estimation. In ICCV, pages 2603– 2610. IEEE, 2011. 1
[20] T. Wittman. Manifold learning matlab demo. URL: http://www. math. umn. edu/ wittman/mani/index. html, 2005. 5
[21] C. Zhang, J. Wang, N. Zhao, and D. Zhang. Reconstruction and analysis of multi-pose face images based on nonlinear dimensionality reduction. Pattern Recognition, 37(2):325– 336, 2004. 1, 6, 7, 8
[22] L. Zhang, S. Wang, and D. Samaras. Face synthesis and recognition from a single image under arbitrary unknown lighting using a spherical harmonic basis morphable model. In CVPR, volume 2, pages 209–216. IEEE, 2005. 1
[23] Z. Zhang, J. Wang, and H. Zha. Adaptive manifold learning. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 34(2):253–265, 2012. 4
[24] Z. Zhang and H. Zha. Principal manifolds and nonlinear dimensionality reduction via tangent space alignment. SIAM Journal on Scientific Computing, 26(1):3 13–338, 2004. 5 2215