Top

International Journal of Computer Vision

Published in:

01-09-2015

Learning Sparse FRAME Models for Natural Image Patterns

Authors: Jianwen Xie, Wenze Hu, Song-Chun Zhu, Ying Nian Wu

Published in: International Journal of Computer Vision | Issue 2-3/2015

Activate our intelligent search to find suitable subject content or patents.

search-config

AI-assisted search

Off

Abstract

It is well known that natural images admit sparse representations by redundant dictionaries of basis functions such as Gabor-like wavelets. However, it is still an open question as to what the next layer of representational units above the layer of wavelets should be. We address this fundamental question by proposing a sparse FRAME (Filters, Random field, And Maximum Entropy) model for representing natural image patterns. Our sparse FRAME model is an inhomogeneous generalization of the original FRAME model. It is a non-stationary Markov random field model that reproduces the observed statistical properties of filter responses at a subset of selected locations, scales and orientations. Each sparse FRAME model is intended to represent an object pattern and can be considered a deformable template. The sparse FRAME model can be written as a shared sparse coding model, which motivates us to propose a two-stage algorithm for learning the model. The first stage selects the subset of wavelets from the dictionary by a shared matching pursuit algorithm. The second stage then estimates the parameters of the model given the selected wavelets. Our experiments show that the sparse FRAME models are capable of representing a wide variety of object patterns in natural images and that the learned models are useful for object classification.

previous article Guest Editorial: Sparse Coding

next article Extrinsic Methods for Coding and Dictionary Learning on Grassmann Manifolds

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

inform now

Available only for authorised users

Ackley, D. H., Hinton, G. E., & Sejnowski, T. J. (1985). A learning algorithm for Boltzmann machines. Cognitive Science, 9, 147–169.CrossRef

Adler, A., Elad, M., & Hel-Or, Y. (2013). Probabilistic Subspace Clustering via Sparse Representations. IEEE Signal Processing Letters, 20, 63–66.CrossRef

Aharon, M., Elad, M., & Bruckstein, A. M. (2006). The K-SVD: An algorithm for designing of overcomplete dictionaries for sparse representation. IEEE Transactions on Signal Processing, 54, 4311–4322.CrossRef

Bengio, Y., Courville, A. C., & Vincent, P. (2013). Representation learning: A review and new perspectives. IEEE Transactions on PAMI, 35, 1798–1828.

Bruckstein, A. M., Donoho, D. L., & Elad, M. (2009). From sparse solutions of systems of equations to sparse modeling of signals and images. SIAM Review, 51, 34–81.CrossRefMathSciNetMATH

Chen, S. S., Donoho, D. L., & Saunders, M. A. (2001). Atomic decomposition by basis pursuit. SIAM Review, 43, 129–159.CrossRefMathSciNetMATH

Chen, J., & Huo, X. (2005). Sparse representations for multiple measurements vectors (mmv) in an overcomplete dictionary. In: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 4, pp. 257–260.

Dalal, N., & Triggs, B. (2005). Histograms of oriented gradients for human detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 1, pp. 886-893.

Dempster, A. P., Laird, N. M., & Rubin, D. B. (1977). Maximum-likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society B, 39, 1–38.MathSciNetMATH

Duane, S., Kennedy, A. D., Pendleton, B. J., & Roweth, D. (1987). Hybrid Monte Carlo. Physics Letters, 195, 216–222.CrossRef

Elad, M. (2010). Sparse and redundant representations: From theory to applications in signal and image processing. Berlin: Springer.CrossRef

Elad, M., & Aharon, M. (2006). Image denoising via sparse and redundant representations over learned dictionaries. IEEE Transactions Image Processing, 15, 3736–3745.CrossRefMathSciNet

Elad, M., Milanfar, P., & Rubinstein, R. (2007). Analysis versus synthesis in signal priors. Inverse problems, 23(3), 947.

Fan, R. E., Chang, K. W., Hsieh, C. J., Wang, X. R., & Lin, C. J. (2008). LIBLINEAR: A library for large linear classication. Journal of Machine Learning Research, 9, 1871–1874.MATH

Fei-Fei, L., Fergus, R., & Perona, P. (2004). Learning generative visual models from few training examples: An incremental Bayesian approach tested on 101 object categories. In: Procedings of the Computer Vision and Pattern Recognition Workshops.

Felzenszwalb, P., Girshick, R., McAllester, D., & Ramanan, D. (2010). Object detection with discriminatively trained part-based models. IEEE Transactions on PAMI, 32, 1627–1645.CrossRef

Ferrari, V., Jurie, F., & Schmid, C. (2010). From images to shape models for object detection. International Journal of Computer Vision, 87, 284–303.

Fidler, S., Boben, M. & Leonardis, A. (2008). Similarity-based cross-layered hierarchical representation for object categorization. In: Proceedings of the IEEE Conference on Computer Vision and PatternRecognition (CVPR).

Friedman, J. H. (1987). Exploratory projection pursuit. Journal of the American Statistical Association, 82, 249–266.CrossRefMathSciNet

Gelman, A., & Meng, X. L. (1998). Simulating normalizing constants: from importance sampling to bridge sampling to path sampling. Statistical Science, 13, 163–185.CrossRefMathSciNetMATH

Geman, S., & Geman, D. (1984). Stochastic relaxation, Gibbs distribution, and the Bayesian restoration of images. IEEE Transactions on PAMI, 6, 721–741.CrossRefMATH

Geman, S., Potter, D. F., & Chi, Z. (2002). Composition systems. Quarterly of Applied Mathematics, 60, 707–736.MathSciNetMATH

Gong, B., Shi, Y., Sha, F. & Grauman, K. (2012). Geodesic flow kernel for unsupervised domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

Gopalan, R., Li, R., & Chellappa, R. (2011). Domain adaptation for object recognition: an unsupervised approach. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV).

Griffin, G., Holub, A., & Perona, P. (2007). Caltech-256 object category dataset. Caltech: Technical report.

Hinton, G. E. (2002). Training products of experts by minimizing contrastive divergence. Neural Computation, 14, 1771–1800.CrossRefMATH

Hinton, G. E., Osindero, S., & Teh, Y. (2006). A fast learning algorithm for deep belief nets. Neural Computation, 18, 1527–1554.CrossRefMathSciNetMATH

Hoffman, J., Rodner, E., Donahue, J., Saenko, K., & Darrell, T. (2013). Efficient learning of domain-invariant image representations. In: Proceedings of the International Conference of Learning Representations.

Hong, Y., Si, Z., Hu, W., Zhu, S. C., & Wu, Y. N. (2013). Unsupervised learning of compositional sparse code for natural image representation. Quarterly of Applied Mathematics, 72, 373–406.CrossRefMathSciNet

Jhou, I., Liu, D., Lee, D. T. & Chang, S. (2012). Robust visual domain adaptation with low-rank reconstruction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

Lazebnik, S., Schmid, C., & Ponce, J. (2006). Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: Proceedings of the IEEE Conference on Computer Vision and PatternRecognition (CVPR)..

Lee, H., Grosse, R., Ranganath, R., & Ng, A. Y. (2009). Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. In: Proceedings of the 26th Annual International Conference on Machine Learning.

Liu, C., Zhu, S.-C., & Shum, H.-Y. (2001). Learning inhomogeneous gibbs model of faces by minimax entropy. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 281–287.

Lounici, K., Tsybakov, A. B., Pontil, M., & van de Geer, S. A. (2009). Taking advantage of sparsity in multi-task learning. In: Proceedings of the 22nd Conference on Learning Theory.

Lowe, D. (2004). Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60, 91–110.

Mallat, S., & Zhang, Z. (1993). Matching pursuit in a time-frequency dictionary. IEEE Transactions on Signal Processing, 41, 3397–3415.CrossRefMATH

Marszalek, M., & Schmid, C. (2007). Accurate object localization with shape masks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

Nama, S., Daviesb, M. E., Eladc, M., & Gribonval, R. (2013). The cosparse analysis model and algorithms. Applied and Computational Harmonic Analysis, 34, 30–56.CrossRefMathSciNet

Neal, R. (2001). Annealed importance sampling. Statistics and Computing, 11, 125–139.CrossRefMathSciNet

Neal, R. (2011). MCMC using Hamiltonian dynamics. Handbook of Markov Chain Monte Carlo.

Obozinski, G., Wainwright, M. J., & Jordan, M. I. (2011). Support union recovery in high-dimensional multivariate regression. Annals of Statistics, 39, 1–47.CrossRefMathSciNetMATH

Olshausen, B. A., & Field, D. J. (1996). Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature, 381, 607–609.CrossRef

Pati, Y. C., Rezaiifar, R., & Krishnaprasad, P. S. (1993). Orthogonal matching pursuit: Recursive function approximation with applications to wavelet decomposition. In: Proceedings of the 27th Asilomar Conference on Signals, Systems and Computers, pp. 40–44.

Pietra, S. D., Pietra, V. D., & Lafferty, J. (1997). Inducing features of random fields. IEEE Transactions on PAMI, 19, 380–393.

Ranzato, M., & Hinton, G. E. (2010). Modeling pixel means and covariances using factorized third-order Boltzmann machines. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

Riesenhuber, M., & Poggio, T. (1999). Hierarchical models of object recognition in cortex. Nature Neuroscience, 2, 1019–1025.CrossRef

Roth, S., & Black, M. (2009). Fields of experts. International Journal of Computer Vision, 82, 205–229.

Rubinstein, R., Zibulevsky, M., & Elad, M. (2010). Double sparsity: Learning sparse dictionaries for sparse signal approximation. IEEE Transactions on Signal Processing, 58, 1553–1564.CrossRefMathSciNet

Saenko, K., Kulis, B., Fritz, M. & Darrell, T. (2010). Adapting visual category models to new domains. In: Proceedings of the European Conference on Computer Vision (ECCV).

Shekhar, S., Patel, V. M., Nguyen, H. V., & Chellappa, R. (2013). Generalized domain adaptive dictionaries. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

Si, Z., & Zhu, S. C. (2012). Learning hybrid image template (HIT) by information projection. IEEE Transactions on PAMI, 34, 1354–1367.CrossRef

Smolensky, P. (1986). Information processing in dynamical systems: Foundations of harmony theory. In D. E. Rumelhart & J. L. McClelland (Eds.), Parallel distributed processing (pp. 194–281). Cambridge: MIT Press.

Teh, Y. W., Welling, M., Osindero, S., & Hinton, G. E. (2003). Energy-based models for sparse overcomplete representations. Journal of Machine Learning Research, 4, 1235–1260.

Tibshirani, R. (1996). Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society, B, 58, 267–288.MathSciNetMATH

Tropp, J., Gilbert, A., & Straus, M. (2006). Algorithms for simultaneous sparse approximation. part I: Greedy pursuit. Journal of Signal Processing, 86, 572–588.CrossRefMATH

Tuytelaars, T., Lampert, C. H., Blaschko, M. B., & Buntine, W. (2009). Unsupervised object discovery: A comparison. International Journal of Computer Vision, 88(2), 284-302.

Vapnik, V. N. (2000). The nature of statistical learning theory. Berlin: Springer.

Welling, M., Hinton, G. E., & Osindero, S. (2003). Learning sparse topographic representations with products of student-t distributions. In: Proceedings of Advances in Neural Information Processing Systems (NIPS).

Wu, Y. N., Si, Z., Gong, H., & Zhu, S. C. (2010). Learning active basis model for object detection and recognition. International Journal of Computer Vision, 90, 198–235.

Xie, J., Hu, W., Zhu, S. C., & Wu, Y. N. (2014). Learning Inhomogeneous FRAME models for object patterns. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

Yang, M., Zhang, L., Feng, X., & Zhang, D. (2011). Fisher discrimination dictionary learning for sparse representation. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 543-550.

Younes, L. (1999). On the convergence of Markovian stochastic algorithms with rapidly decreasing ergodicity rates. Stochastics and Stochastic Reports, 65, 177–228.CrossRefMathSciNetMATH

Zeiler, M., Taylor, G., & Fergus, R. (2011). Adaptive deconvolutional networks for mid and high level feature learning. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV).

Zhu, L., Lin, C., Huang, H., Chen, Y., & Yuille, A. (2008). Unsupervised structure learning: hierarchical recursive composition, suspicious coincidence and competitive exclusion. In: Proceedings of the European Conference on Computer Vision (ECCV).

Zhu, S. C., & Mumford, D. B. (2006). A stochastic grammar of images. Foundations and Trends in Computer Graphics and Vision, 2, 259–362.CrossRefMATH

Zhu, S. C., Wu, Y. N., & Mumford, D. B. (1998). Minimax entropy principle and its application to texture modeling. Neural Computation, 9, 1627–1660.CrossRef

Title: Learning Sparse FRAME Models for Natural Image Patterns
Authors: Jianwen Xie
Wenze Hu
Song-Chun Zhu
Ying Nian Wu
Publication date: 01-09-2015
Publisher: Springer US
Published in: International Journal of Computer Vision / Issue 2-3/2015
Print ISSN: 0920-5691
Electronic ISSN: 1573-1405
DOI: https://doi.org/10.1007/s11263-014-0757-x

Springer Professional

Abstract

Please log in to get access to your license.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Wirtschaft"

Springer Professional "Technik"

Other articles of this Issue 2-3/2015

Dictionary Learning for Fast Classification Based on Soft-thresholding

Toward Fast Transform Learning

A Bimodal Co-sparse Analysis Model for Image Processing

Collaborative Linear Coding for Robust Image Classification

Efficient Dictionary Learning with Sparseness-Enforcing Projections

Image Deblurring with Coupled Dictionary Learning

Premium Partner