Learning sparse covariance patterns for natural scenes

For scene classification, patch-level linear features do not always work as well as handcrafted features. In this paper, we present a new model to greatly improve the usefulness of linear features in classification by introducing co-variance patterns. We analyze their properties, discuss the fundamental importance, and present a generative model to properly utilize them. With this set of covariance information, in our framework, even the most naive linear features that originally lack the vital ability in classification become powerful. Experiments show that the performance of our new covariance model based on linear features is comparable with or even better than handcrafted features in scene classification.

[1]  Stephen P. Boyd,et al.  Determinant Maximization with Linear Matrix Inequality Constraints , 1998, SIAM J. Matrix Anal. Appl..

[2]  Antonio Torralba,et al.  Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope , 2001, International Journal of Computer Vision.

[3]  Antonio Torralba,et al.  SIFT Flow: Dense Correspondence across Scenes and Its Applications , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Pietro Perona,et al.  A Bayesian hierarchical model for learning natural scene categories , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[5]  James M. Rehg,et al.  CENTRIST: A Visual Descriptor for Scene Categorization , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[7]  Thomas Serre,et al.  Object recognition with features inspired by visual cortex , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[8]  Fatih Murat Porikli,et al.  Region Covariance: A Fast Descriptor for Detection and Classification , 2006, ECCV.

[9]  Vincent Lepetit,et al.  Are sparse representations really relevant for image classification? , 2011, CVPR 2011.

[10]  J L Gallant,et al.  Sparse coding and decorrelation in primary visual cortex during natural vision. , 2000, Science.

[11]  Te-Won Lee,et al.  On the multivariate Laplace distribution , 2006, IEEE Signal Processing Letters.

[12]  Vassilios Morellas,et al.  Tensor Sparse Coding for Region Covariances , 2010, ECCV.

[13]  P. Tseng.  Convergence of a Block Coordinate Descent Method for Nondifferentiable Minimization , 2001 .

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

[15]  Yihong Gong,et al.  Linear spatial pyramid matching using sparse coding for image classification , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Michael Elad,et al.  Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries , 2006, IEEE Transactions on Image Processing.

[17]  Jean Ponce,et al.  Learning mid-level features for recognition , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[18]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[19]  Aapo Hyvärinen,et al.  Natural Image Statistics - A Probabilistic Approach to Early Computational Vision , 2009, Computational Imaging and Vision.

[20]  Andrew Y. Ng,et al.  The Importance of Encoding Versus Training with Sparse Coding and Vector Quantization , 2011, ICML.

[21]  Yihong Gong,et al.  Linear spatial pyramid matching using sparse coding for image classification , 2009, CVPR.

[22]  Graham W. Taylor,et al.  Deconvolutional networks , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[23]  Cordelia Schmid,et al.  Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[24]  Yoshua Bengio,et al.  Greedy Layer-Wise Training of Deep Networks , 2006, NIPS.

[25]  Fatih Murat Porikli,et al.  Pedestrian Detection via Classification on Riemannian Manifolds , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[27]  Ke Huang,et al.  Sparse Representation for Signal Classification , 2006, NIPS.

[28]  Thomas S. Huang,et al.  Image super-resolution as sparse representation of raw image patches , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[29]  Antonio Torralba,et al.  Recognizing indoor scenes , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[30]  Vassilios Morellas,et al.  Positive definite dictionary learning for region covariances , 2011, 2011 International Conference on Computer Vision.

[31]  Michael S. Lewicki,et al.  Emergence of complex cell properties by learning to generalize in natural scenes , 2009, Nature.

[32]  Michael S. Lewicki,et al.  Is Early Vision Optimized for Extracting Higher-order Dependencies? , 2005, NIPS.

[33]  Svetlana Lazebnik,et al.  Scene recognition and weakly supervised object localization with deformable part-based models , 2011, 2011 International Conference on Computer Vision.

[34]  Jiayan Jiang,et al.  Learning a mixture of sparse distance metrics for classification and dimensionality reduction , 2011, 2011 International Conference on Computer Vision.

[35]  John D. Lafferty,et al.  Learning image representations from the pixel level via hierarchical sparse coding , 2011, CVPR 2011.

[36]  Krista A. Ehinger,et al.  SUN database: Large-scale scene recognition from abbey to zoo , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[37]  Rong Jin,et al.  An Information Geometry Approach for Distance Metric Learning , 2009, AISTATS.