Cornet: Composite-Regularized Neural Network For Convolutional Sparse Coding

Sparse recovery via composite regularization is an interesting approach proposed recently in the literature. One could design nonconvex regularizers through a convex combination of sparsitypromoting penalties with known proximal operators. We develop a new algorithm, namely, convolutional proximal-averaged thresholding algorithm (C-PATA) for composite-regularized convolutional sparse coding (CR-CSC) based on the recently proposed idea of proximal averaging. We develop an autoencoder structure based on the deep-unfolding of C-PATA iterations into neural network layers, which results in the composite-regularized neural network (CoRNet) architecture. The convolutional learned iterative soft-thresholding algorithm becomes a special case of CoRNet. We demonstrate the efficacy of CoRNet considering applications to image denoising and inpainting, and compare the performance with state-of-the-art techniques such as BM3D, convolutional LISTA, and fast and flexible convolutional sparse coding (FFCSC).

[1]  Michael Elad,et al.  RED-UCATION: A Novel CNN Architecture Based on Denoising Nonlinearities , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[2]  Jieping Ye,et al.  A General Iterative Shrinkage and Thresholding Algorithm for Non-convex Regularized Optimization Problems , 2013, ICML.

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

[4]  Michael Elad,et al.  Convolutional Dictionary Learning via Local Processing , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[5]  José Carlos Príncipe,et al.  A fast proximal method for convolutional sparse coding , 2013, The 2013 International Joint Conference on Neural Networks (IJCNN).

[6]  Thomas S. Huang,et al.  Image super-resolution as sparse representation of raw image patches , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Alessandro Foi,et al.  Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering , 2007, IEEE Transactions on Image Processing.

[8]  Filip Sroubek,et al.  Fast convolutional sparse coding using matrix inversion lemma , 2016, Digit. Signal Process..

[9]  Raja Giryes,et al.  Learned Convolutional Sparse Coding , 2017, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

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

[11]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[12]  Stamatios Lefkimmiatis,et al.  Universal Denoising Networks : A Novel CNN Architecture for Image Denoising , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[13]  Brendt Wohlberg,et al.  Boundary handling for convolutional sparse representations , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[14]  Ali Mousavi,et al.  Learning to invert: Signal recovery via Deep Convolutional Networks , 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[15]  Cun-Hui Zhang.  Nearly unbiased variable selection under minimax concave penalty , 2010, 1002.4734.

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

[17]  Brendt Wohlberg,et al.  Efficient Algorithms for Convolutional Sparse Representations , 2016, IEEE Transactions on Image Processing.

[18]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[19]  Stephen P. Boyd,et al.  Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers , 2011, Found. Trends Mach. Learn..

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

[21]  Yann LeCun,et al.  Learning Fast Approximations of Sparse Coding , 2010, ICML.

[22]  Wolfgang Heidrich,et al.  Imaging in scattering media using correlation image sensors and sparse convolutional coding. , 2014, Optics express.

[23]  Leon Wenliang Zhong,et al.  Gradient Descent with Proximal Average for Nonconvex and Composite Regularization , 2014, AAAI.

[24]  Robert D. Nowak,et al.  Majorization–Minimization Algorithms for Wavelet-Based Image Restoration , 2007, IEEE Transactions on Image Processing.

[25]  Lei Zhang,et al.  Convolutional Sparse Coding for Image Super-Resolution , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[26]  Ulugbek Kamilov,et al.  A Parallel Proximal Algorithm for Anisotropic Total Variation Minimization , 2017, IEEE Transactions on Image Processing.

[27]  Simon Lucey,et al.  Optimization Methods for Convolutional Sparse Coding , 2014, ArXiv.

[28]  Tianzhu Zhang,et al.  In Defense of Sparse Tracking: Circulant Sparse Tracker , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[29]  A. Bruckstein,et al.  On the uniqueness of overcomplete dictionaries, and a practical way to retrieve them , 2006 .

[30]  Gordon Wetzstein,et al.  Consensus Convolutional Sparse Coding , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[31]  Gordon Wetzstein,et al.  Fast and flexible convolutional sparse coding , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[32]  Lei Zhang,et al.  FFDNet: Toward a Fast and Flexible Solution for CNN-Based Image Denoising , 2017, IEEE Transactions on Image Processing.

[33]  Jianqing Fan,et al.  Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties , 2001 .