Momen^et: Flavor the Moments in Learning to Classify Shapes

A fundamental question in learning to classify 3D shapes is how to treat the data in a way that would allow us to construct efficient and accurate geometric processing and analysis procedures. Here, we restrict ourselves to networks that operate on point clouds. There were several attempts to treat point clouds as non-structured data sets by which a neural network is trained to extract discriminative properties. The idea of using 3D coordinates as class identifiers motivated us to extend this line of thought to that of shape classification by comparing attributes that could easily account for the shape moments. Here, we propose to add polynomial functions of the coordinates allowing the network to account for higher order moments of a given shape. Experiments on two benchmarks show that the suggested network is able to provide state of the art results and at the same token learn more efficiently in terms of memory and computational complexity.

[1]  Demetri Psaltis,et al.  Recognitive Aspects of Moment Invariants , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Jianxiong Xiao,et al.  3D ShapeNets: A deep representation for volumetric shapes , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Jing Huang,et al.  Point cloud labeling using 3D Convolutional Neural Network , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

[4]  Victor S. Lempitsky,et al.  Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[5]  Ernest L. Hall,et al.  Three-Dimensional Moment Invariants , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Chris Dyer,et al.  Neural Arithmetic Logic Units , 2018, NeurIPS.

[7]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[8]  Dong Tian,et al.  Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[9]  C. Lee Giles,et al.  Encoding Geometric Invariances in Higher-Order Neural Networks , 1987, NIPS.

[10]  Alexander M. Bronstein,et al.  Numerical Geometry of Non-Rigid Shapes , 2009, Monographs in Computer Science.

[11]  Theodore Lim,et al.  Generative and Discriminative Voxel Modeling with Convolutional Neural Networks , 2016, ArXiv.

[12]  Sebastian Scherer,et al.  VoxNet: A 3D Convolutional Neural Network for real-time object recognition , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[13]  Anath Fischer,et al.  3DmFV: Three-Dimensional Point Cloud Classification in Real-Time Using Convolutional Neural Networks , 2018, IEEE Robotics and Automation Letters.

[14]  Dmitry Yarotsky,et al.  Error bounds for approximations with deep ReLU networks , 2016, Neural Networks.

[15]  Leonidas J. Guibas,et al.  Volumetric and Multi-view CNNs for Object Classification on 3D Data , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Subhransu Maji,et al.  Multi-view Convolutional Neural Networks for 3D Shape Recognition , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[17]  Sainan Liu,et al.  Attentional ShapeContextNet for Point Cloud Recognition , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[18]  T. A. Springer.  The Algebra of Invariants , 2007 .

[19]  Jiaxin Li,et al.  SO-Net: Self-Organizing Network for Point Cloud Analysis , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[20]  Yue Wang,et al.  Dynamic Graph CNN for Learning on Point Clouds , 2018, ACM Trans. Graph..

[21]  Yaron Lipman,et al.  Point convolutional neural networks by extension operators , 2018, ACM Trans. Graph..

[22]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[23]  C. L. Giles,et al.  Machine learning using higher order correlation networks , 1986 .

[24]  Ulrich Neumann,et al.  Recurrent Slice Networks for 3D Segmentation of Point Clouds , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[25]  Colin Giles,et al.  Learning, invariance, and generalization in high-order neural networks. , 1987, Applied optics.

[26]  Alireza Khotanzad,et al.  Invariant Image Recognition by Zernike Moments , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[27]  Gernot Riegler,et al.  OctNet: Learning Deep 3D Representations at High Resolutions , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  W. Atchley,et al.  THE GEOMETRY OF CANONICAL VARIATE ANALYSIS , 1981 .

[29]  Roland T. Chin,et al.  On Image Analysis by the Methods of Moments , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[30]  Silvio Savarese,et al.  Joint 2D-3D-Semantic Data for Indoor Scene Understanding , 2017, ArXiv.

[31]  Anath Fischer,et al.  3D Point Cloud Classification and Segmentation using 3D Modified Fisher Vector Representation for Convolutional Neural Networks , 2017, ArXiv.

[32]  Andrew Zisserman,et al.  Spatial Transformer Networks , 2015, NIPS.

[33]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[34]  Gary William Flake,et al.  Square Unit Augmented, Radially Extended, Multilayer Perceptrons , 1996, Neural Networks: Tricks of the Trade.

[35]  R. Srikant,et al.  Why Deep Neural Networks for Function Approximation? , 2016, ICLR.

[36]  Alexander J. Smola,et al.  Deep Sets , 2017, 1703.06114.

[37]  Nikos Komodakis,et al.  Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[38]  Yasuyuki Matsushita,et al.  RotationNet: Joint Object Categorization and Pose Estimation Using Multiviews from Unsupervised Viewpoints , 2016, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[39]  Leonidas J. Guibas,et al.  PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[40]  Binh-Son Hua,et al.  Pointwise Convolutional Neural Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[41]  Leonidas J. Guibas,et al.  PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space , 2017, NIPS.

[42]  Anthony P. Reeves,et al.  Three-Dimensional Shape Analysis Using Moments and Fourier Descriptors , 1988, IEEE Trans. Pattern Anal. Mach. Intell..