3D Object Classification Using Deep Belief Networks

Extracting features with strong expressive and discriminative ability is one of key factors for the effectiveness of 3D model classifier. Lots of research work has illustrated that deep belief networks (DBN) have enough power to represent the distributions of input data. In this paper, we apply DBN for extracting the features of 3D model. After implementing a contrastive divergence method, we obtain a trained-well DBN, which can powerfully represent the input data. Therefore, the feature from the output of last layer is acquired. This procedure is unsupervised. Due to the limit of labeled data, a semi-supervised method is utilized to recognize 3D objects using the feature obtained from the trained DBN. The experiments are conducted in the publicly available Princeton Shape Benchmark (PSB), and the experimental results demonstrate the effectiveness of our method.

[1]  Qi Tian,et al.  Task-Dependent Visual-Codebook Compression , 2012, IEEE Transactions on Image Processing.

[2]  Yue Gao,et al.  View-based 3D model retrieval with probabilistic graph model , 2010, Neurocomputing.

[3]  Ioannis Pratikakis,et al.  PANORAMA: A 3D Shape Descriptor Based on Panoramic Views for Unsupervised 3D Object Retrieval , 2010, International Journal of Computer Vision.

[4]  Xindong Wu,et al.  3-D Object Retrieval With Hausdorff Distance Learning , 2014, IEEE Transactions on Industrial Electronics.

[5]  Avrim Blum,et al.  Learning from Labeled and Unlabeled Data using Graph Mincuts , 2001, ICML.

[6]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..

[7]  Zheng Qin,et al.  A powerful relevance feedback mechanism for content-based 3D model retrieval , 2007, Multimedia Tools and Applications.

[8]  Michael G. Strintzis,et al.  Efficient 3-D model search and retrieval using generalized 3-D radon transforms , 2006, IEEE Transactions on Multimedia.

[9]  Yue Gao,et al.  View-based 3D object retrieval by bipartite graph matching , 2012, ACM Multimedia.

[10]  Giuseppe Patanè,et al.  A Minimal Contouring Approach to the Computation of the Reeb Graph , 2009, IEEE Transactions on Visualization and Computer Graphics.

[11]  Dejan V. Vranic.  DESIRE: a composite 3D-shape descriptor , 2005, 2005 IEEE International Conference on Multimedia and Expo.

[12]  Thomas A. Funkhouser,et al.  The Princeton Shape Benchmark , 2004, Proceedings Shape Modeling Applications, 2004..

[13]  Peter K. Allen,et al.  SHREC’08 entry: Training set expansion via autotags , 2008, 2008 IEEE International Conference on Shape Modeling and Applications.

[14]  Miguel Á. Carreira-Perpiñán,et al.  On Contrastive Divergence Learning , 2005, AISTATS.

[15]  Petros Daras,et al.  A 3D Shape Retrieval Framework Supporting Multimodal Queries , 2010, International Journal of Computer Vision.

[16]  Qi Tian,et al.  Less is More: Efficient 3-D Object Retrieval With Query View Selection , 2011, IEEE Transactions on Multimedia.

[17]  Zhang Xiong,et al.  ModelSeek: an effective 3D model retrieval system , 2011, Multimedia Tools and Applications.

[18]  Tao,et al.  MATE： A Visual Based 3D Shape Descriptor , 2009 .

[19]  Yue Gao,et al.  3D model comparison using spatial structure circular descriptor , 2010, Pattern Recognit..

[20]  Bernhard Schölkopf,et al.  Learning with Local and Global Consistency , 2003, NIPS.

[21]  Yue Gao,et al.  3-D Object Retrieval and Recognition With Hypergraph Analysis , 2012, IEEE Transactions on Image Processing.

[22]  Kilian Q. Weinberger,et al.  Distance Metric Learning for Large Margin Nearest Neighbor Classification , 2005, NIPS.

[23]  Geoffrey E. Hinton,et al.  Deep, Narrow Sigmoid Belief Networks Are Universal Approximators , 2008, Neural Computation.

[24]  Yue Gao,et al.  3D object retrieval with bag-of-region-words , 2010, ACM Multimedia.

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

[26]  Jun-Bao Li,et al.  3D model classification based on nonparametric discriminant analysis with kernels , 2011, Neural Computing and Applications.

[27]  Xuelong Li,et al.  Spectral-Spatial Constraint Hyperspectral Image Classification , 2014, IEEE Transactions on Geoscience and Remote Sensing.

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

[29]  Biao Leng,et al.  Support Vector Machine active learning for 3D model retrieval , 2007 .

[30]  Yue Gao,et al.  Camera Constraint-Free View-Based 3-D Object Retrieval , 2012, IEEE Transactions on Image Processing.

[31]  Ioannis Pratikakis,et al.  Efficient 3D shape matching and retrieval using a concrete radialized spherical projection representation , 2007, Pattern Recognit..

[32]  Peter K. Allen,et al.  Autotagging to improve text search for 3d models , 2008, Shape Modeling International.

[33]  Nicolas Le Roux,et al.  Representational Power of Restricted Boltzmann Machines and Deep Belief Networks , 2008, Neural Computation.

[34]  Zhang Xiong,et al.  A 3D shape retrieval framework for 3D smart cities , 2010, Frontiers of Computer Science in China.

[35]  Liqun Li,et al.  MADE: A Composite Visual-Based 3D Shape Descriptor , 2007, MIRAGE.

[36]  Grgoire Montavon,et al.  Neural Networks: Tricks of the Trade , 2012, Lecture Notes in Computer Science.

[37]  Jong-Soo Choi,et al.  A new shape descriptor using sliced image histogram for 3D model retrieval , 2009, IEEE Transactions on Consumer Electronics.

[38]  Geoffrey E. Hinton.  A Practical Guide to Training Restricted Boltzmann Machines , 2012, Neural Networks: Tricks of the Trade.

[39]  Zheng Qin,et al.  Automatic Combination of Feature Descriptors for Effective 3D Shape Retrieval , 2007, MIRAGE.

[40]  Mohamed Daoudi,et al.  A Bayesian 3-D Search Engine Using Adaptive Views Clustering , 2007, IEEE Transactions on Multimedia.