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

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

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

[4]  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.

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

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

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

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

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

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

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

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

[13]  Pascal Fua,et al.  Learning rotational features for filament detection , 2009, CVPR.

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

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

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

[17]  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 .

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

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

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

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

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

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

[24]  C. J. van Rijsbergen,et al.  FOUNDATION OF EVALUATION , 1974 .

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

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

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

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

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

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

[31]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

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

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

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

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

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

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

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

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

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

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

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

[43]  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.

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

[45]  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).

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