FOCNet: A Fractional Optimal Control Network for Image Denoising

Deep convolutional neural networks (DCNN) have been successfully used in many low-level vision problems such as image denoising. Recent studies on the mathematical foundation of DCNN has revealed that the forward propagation of DCNN corresponds to a dynamic system, which can be described by an ordinary differential equation (ODE) and solved by the optimal control method. However, most of these methods employ integer-order differential equation, which has local connectivity in time space and cannot describe the long-term memory of the system. Inspired by the fact that the fractional-order differential equation has long-term memory, in this paper we develop an advanced image denoising network, namely FOCNet, by solving a fractional optimal control (FOC) problem. Specifically, the network structure is designed based on the discretization of a fractional-order differential equation, which enjoys long-term memory in both forward and backward passes. Besides, multi-scale feature interactions are introduced into the FOCNet to strengthen the control of the dynamic system. Extensive experiments demonstrate the leading performance of the proposed FOCNet on image denoising. Code will be made available.

[1]  Eldad Haber,et al.  Deep Neural Networks Motivated by Partial Differential Equations , 2018, Journal of Mathematical Imaging and Vision.

[2]  Gregory Shakhnarovich,et al.  FractalNet: Ultra-Deep Neural Networks without Residuals , 2016, ICLR.

[3]  Jitendra Malik,et al.  Scale-Space and Edge Detection Using Anisotropic Diffusion , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Narendra Ahuja,et al.  Single image super-resolution from transformed self-exemplars , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  I. Petráš.  Fractional-Order Nonlinear Systems: Modeling, Analysis and Simulation , 2011 .

[6]  M. Edelman.  Universality in Systems with Power-Law Memory and Fractional Dynamics , 2017, 1709.00093.

[7]  Igor Podlubny,et al.  Fractional-order systems and PI/sup /spl lambda//D/sup /spl mu//-controllers , 1999 .

[8]  Bin Dong,et al.  Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equations , 2017, ICML.

[9]  Jian Yang,et al.  MemNet: A Persistent Memory Network for Image Restoration , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[10]  Eirikur Agustsson,et al.  NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[11]  Luigi Fortuna,et al.  Fractional Order Systems: Modeling and Control Applications , 2010 .

[12]  Long Chen,et al.  Maximum Principle Based Algorithms for Deep Learning , 2017, J. Mach. Learn. Res..

[13]  Dahua Lin,et al.  PolyNet: A Pursuit of Structural Diversity in Very Deep Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  YangQuan Chen,et al.  Fractional-order Systems and Controls , 2010 .

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

[16]  Raquel Urtasun,et al.  The Reversible Residual Network: Backpropagation Without Storing Activations , 2017, NIPS.

[17]  Andrea Vedaldi,et al.  MatConvNet: Convolutional Neural Networks for MATLAB , 2014, ACM Multimedia.

[18]  Fernando J. Pineda,et al.  Dynamics and architecture for neural computation , 1988, J. Complex..

[19]  Jong Chul Ye,et al.  Beyond Deep Residual Learning for Image Restoration: Persistent Homology-Guided Manifold Simplification , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[20]  Yu-Bin Yang,et al.  Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections , 2016, NIPS.

[21]  Lei Zhang,et al.  Weighted Nuclear Norm Minimization with Application to Image Denoising , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[22]  E Weinan,et al.  A Proposal on Machine Learning via Dynamical Systems , 2017, Communications in Mathematics and Statistics.

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

[24]  Liang Lin,et al.  Multi-level Wavelet-CNN for Image Restoration , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[25]  Xiangchu Feng,et al.  Adaptive regularizer learning for low rank approximation with application to image denoising , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

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

[27]  M. Edelman.  Fractional Dynamical Systems , 2013, 1401.0048.

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

[29]  John R. Anderson.  Learning and memory: An integrated approach, 2nd ed. , 2000 .

[30]  Yunjin Chen,et al.  Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[31]  Lei Zhang,et al.  Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising , 2016, IEEE Transactions on Image Processing.

[32]  Jean-Michel Morel,et al.  A non-local algorithm for image denoising , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[33]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[34]  Eldad Haber,et al.  Stable architectures for deep neural networks , 2017, ArXiv.

[35]  F. Lobo Pereira,et al.  A new approach to the Pontryagin maximum principle for nonlinear fractional optimal control problems , 2015, 1503.07720.

[36]  Stefan Roth,et al.  Neural Nearest Neighbors Networks , 2018, NeurIPS.

[37]  Otmar Scherzer,et al.  Variational Methods in Imaging , 2008, Applied mathematical sciences.

[38]  Jian Bai,et al.  Fractional-Order Anisotropic Diffusion for Image Denoising , 2007, IEEE Transactions on Image Processing.

[39]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[40]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[41]  L. Rudin,et al.  Nonlinear total variation based noise removal algorithms , 1992 .

[42]  Jitendra Malik,et al.  A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[43]  M. Edelman.  Fractional Maps as Maps with Power-Law Memory , 2013, 1306.6361.

[44]  Michael J. Black,et al.  Fields of Experts , 2009, International Journal of Computer Vision.