Learning Separable Filters

Learning filters to produce sparse image representations in terms of over complete dictionaries has emerged as a powerful way to create image features for many different purposes. Unfortunately, these filters are usually both numerous and non-separable, making their use computationally expensive. In this paper, we show that such filters can be computed as linear combinations of a smaller number of separable ones, thus greatly reducing the computational complexity at no cost in terms of performance. This makes filter learning approaches practical even for large images or 3D volumes, and we show that we significantly outperform state-of-the-art methods on the linear structure extraction task, in terms of both accuracy and speed. Moreover, our approach is general and can be used on generic filter banks to reduce the complexity of the convolutions.

[1]  S. Treitel,et al.  The Design of Multistage Separable Planar Filters , 1971 .

[2]  William M. Shaw,et al.  On the foundation of evaluation , 1986, J. Am. Soc. Inf. Sci..

[3]  Edward H. Adelson,et al.  The Design and Use of Steerable Filters , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Lawrence D. Jackel,et al.  Hardware requirements for neural network pattern classifiers: a case study and implementation , 1992, IEEE Micro.

[5]  C. Gotsman.  Constant‐Time Filtering by Singular Value Decomposition † , 1994 .

[6]  Deformable Kernels for Early Vision , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

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

[8]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[9]  J. van Leeuwen,et al.  Neural Networks: Tricks of the Trade , 2002, Lecture Notes in Computer Science.

[10]  A.D. Hoover,et al.  Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response , 2000, IEEE Transactions on Medical Imaging.

[11]  Stephen P. Boyd,et al.  A rank minimization heuristic with application to minimum order system approximation , 2001, Proceedings of the 2001 American Control Conference. (Cat. No.01CH37148).

[12]  Demetri Terzopoulos,et al.  Multilinear Analysis of Image Ensembles: TensorFaces , 2002, ECCV.

[13]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[14]  Jitendra Malik,et al.  Representing and Recognizing the Visual Appearance of Materials using Three-dimensional Textons , 2001, International Journal of Computer Vision.

[15]  Bernhard Schölkopf,et al.  Face Detection - Efficient and Rank Deficient , 2004, NIPS.

[16]  Max A. Viergever,et al.  Ridge-based vessel segmentation in color images of the retina , 2004, IEEE Transactions on Medical Imaging.

[17]  Tamir Hazan,et al.  Sparse image coding using a 3D non-negative tensor factorization , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[18]  Yann LeCun,et al.  The mnist database of handwritten digits , 2005 .

[19]  John K. Tsotsos,et al.  Applying Ensembles of Multilinear Classifiers in the Frequency Domain , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

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

[21]  Martial Hebert,et al.  Toward Objective Evaluation of Image Segmentation Algorithms , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[23]  Berkant Savas,et al.  Handwritten digit classification using higher order singular value decomposition , 2007, Pattern Recognit..

[24]  Ioannis A. Kakadiaris,et al.  Automatic Centerline Extraction of Irregular Tubular Structures Using Probability Volumes from Multiphoton Imaging , 2007, MICCAI.

[25]  Yacov Hel-Or,et al.  The Gray-Code Filter Kernels , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[26]  M. Meilă.  Comparing clusterings---an information based distance , 2007 .

[27]  Christian Bauckhage.  Tensor-Based Filter Design using Kernel Ridge Regression , 2007, 2007 IEEE International Conference on Image Processing.

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

[29]  Antonio Torralba,et al.  Ieee Transactions on Pattern Analysis and Machine Intelligence 1 80 Million Tiny Images: a Large Dataset for Non-parametric Object and Scene Recognition , 2022 .

[30]  Max W. K. Law,et al.  Three Dimensional Curvilinear Structure Detection Using Optimally Oriented Flux , 2008, ECCV.

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

[32]  Yann LeCun,et al.  What is the best multi-stage architecture for object recognition? , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[33]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[34]  Guillermo Sapiro,et al.  Non-local sparse models for image restoration , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[35]  Tamara G. Kolda,et al.  Tensor Decompositions and Applications , 2009, SIAM Rev..

[36]  P. Fua,et al.  Learning rotational features for filament detection , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[37]  Michael Elad,et al.  Double Sparsity: Learning Sparse Dictionaries for Sparse Signal Approximation , 2010, IEEE Transactions on Signal Processing.

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

[39]  Guillermo Sapiro,et al.  Sparse Representation for Computer Vision and Pattern Recognition , 2010, Proceedings of the IEEE.

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

[41]  Geoffrey E. Hinton,et al.  Learning to Detect Roads in High-Resolution Aerial Images , 2010, ECCV.

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

[43]  Berin Martini,et al.  Hardware accelerated convolutional neural networks for synthetic vision systems , 2010, Proceedings of 2010 IEEE International Symposium on Circuits and Systems.

[44]  Geoffrey E. Hinton.  Learning to represent visual input , 2010, Philosophical Transactions of the Royal Society B: Biological Sciences.

[45]  Daniel M. Dunlavy,et al.  A scalable optimization approach for fitting canonical tensor decompositions , 2011 .

[46]  Gang Hua,et al.  Discriminative Learning of Local Image Descriptors , 1990, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[48]  Julien Mairal,et al.  Convex optimization with sparsity-inducing norms , 2011 .

[49]  F. Bach,et al.  Optimization with Sparsity-Inducing Penalties (Foundations and Trends(R) in Machine Learning) , 2011 .

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

[51]  Vincent Lepetit,et al.  Filter Learning for Linear Structure Segmentation , 2011 .

[52]  Graham W. Taylor,et al.  Adaptive deconvolutional networks for mid and high level feature learning , 2011, 2011 International Conference on Computer Vision.

[53]  Julien Mairal,et al.  Optimization with Sparsity-Inducing Penalties , 2011, Found. Trends Mach. Learn..

[54]  Deva Ramanan,et al.  Steerable part models , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[55]  Christophe Garcia,et al.  Simplifying ConvNets for Fast Learning , 2012, ICANN.

[56]  Jean Ponce,et al.  Task-Driven Dictionary Learning , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[57]  Rasmus Berg Palm,et al.  Prediction as a candidate for learning deep hierarchical models of data , 2012 .

[58]  Klaus-Robert Müller,et al.  Efficient BackProp , 2012, Neural Networks: Tricks of the Trade.

[59]  Vincent Lepetit,et al.  Learning Separable Filters , 2013, CVPR.

[60]  Anders P. Eriksson,et al.  Fast Convolutional Sparse Coding , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[61]  Martin Kleinsteuber,et al.  Separable Dictionary Learning , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[62]  Misha Denil,et al.  Predicting Parameters in Deep Learning , 2014 .

[63]  Joan Bruna,et al.  Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation , 2014, NIPS.