Image Hierarchical Representations Models based on Latent Dirichlet Allocation

Existing image layer representations methods are very feed-forward, and then not able to deal with small ambiguities. A probabilistic model is proposed, and it learns and deduces each layer in that hierarchy together. Therefore, we consider a recursive probabilistic decomposition process, and derive a new yielded method based on recursive Latent Dirichlet Allocation. We show 2 significant properties of the novel probabilistic method: 1) pulsing another hierarchical to represent the enhanced results on that smooth method; 2) an entire Bayesian method beats a feed-forward running of the novel method. The method can be evaluated on a criterion recognition dataset. It takes the probability of recursive decomposition process into account, and obtains multilayer structure pyramid LDA derived model through the derivation. Experiments demonstrate that the novel technique beats existing hierarchical approaches, and present better performance

[1]  Marc'Aurelio Ranzato,et al.  Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  PoggioTomaso,et al.  Robust Object Recognition with Cortex-Like Mechanisms , 2007 .

[3]  Gustavo Deco,et al.  Computational neuroscience of vision , 2002 .

[4]  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).

[5]  Sanja Fidler,et al.  Similarity-based cross-layered hierarchical representation for object categorization , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  T. Ferguson.  A Bayesian Analysis of Some Nonparametric Problems , 1973 .

[7]  Thomas L. Griffiths,et al.  Hierarchical Topic Models and the Nested Chinese Restaurant Process , 2003, NIPS.

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

[9]  Yihong Gong,et al.  Training Hierarchical Feed-Forward Visual Recognition Models Using Transfer Learning from Pseudo-Tasks , 2008, ECCV.

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

[11]  Alexei A. Efros,et al.  Discovering objects and their location in images , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[12]  Y-Lan Boureau,et al.  Learning Convolutional Feature Hierarchies for Visual Recognition , 2010, NIPS.

[13]  David G. Lowe,et al.  University of British Columbia. , 1945, Canadian Medical Association journal.

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

[15]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[16]  Gregor Heinrich.  Parameter estimation for text analysis , 2009 .

[17]  Trevor Darrell,et al.  An Additive Latent Feature Model for Transparent Object Recognition , 2009, NIPS.

[18]  Pietro Perona,et al.  Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[19]  David J. Field,et al.  Sparse coding with an overcomplete basis set: A strategy employed by V1? , 1997, Vision Research.

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

[21]  Tai Sing Lee,et al.  Hierarchical Bayesian inference in the visual cortex. , 2003, Journal of the Optical Society of America. A, Optics, image science, and vision.