Deep Transform and Metric Learning Networks

Based on its great successes in inference and denosing tasks, Dictionary Learning (DL) and its related sparse optimization formulations have garnered a lot of research interest. While most solutions have focused on single layer dictionaries, the recently improved Deep DL methods have also fallen short on a number of issues. We hence propose a novel Deep DL approach where each DL layer can be formulated and solved as a combination of one linear layer and a Recurrent Neural Network, where the RNN is flexibly regraded as a layer-associated learned metric. Our proposed work unveils new insights between the Neural Networks and Deep DL, and provides a novel, efficient and competitive approach to jointly learn the deep transforms and metrics. Extensive experiments are carried out to demonstrate that the proposed method can not only outperform existing Deep DL, but also state-of-the-art generic Convolutional Neural Networks.

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

[2]  Thomas Brox,et al.  Striving for Simplicity: The All Convolutional Net , 2014, ICLR.

[3]  Thomas S. Huang,et al.  Deep Networks for Image Super-Resolution with Sparse Prior , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[4]  Liyi Dai,et al.  Analysis Dictionary Learning Based Classification: Structure for Robustness , 2018, IEEE Transactions on Image Processing.

[5]  Erik Skau,et al.  Image classification: A hierarchical dictionary learning approach , 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

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

[7]  Ivor W. Tsang,et al.  SC2Net: Sparse LSTMs for Sparse Coding , 2018, AAAI.

[8]  Kai Zhang,et al.  Class relatedness oriented-discriminative dictionary learning for multiclass image classification , 2016, Pattern Recognit..

[9]  Liyi Dai,et al.  Structured Analysis Dictionary Learning for Image Classification , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

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

[11]  Pier Luigi Dragotti,et al.  A Deep Dictionary Model for Image Super-Resolution , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[12]  Mayank Vatsa,et al.  Deep Dictionary Learning , 2016, IEEE Access.

[13]  Huchuan Lu,et al.  Robust object tracking via sparsity-based collaborative model , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  Patrick L. Combettes,et al.  Deep Neural Network Structures Solving Variational Inequalities , 2018, Set-Valued and Variational Analysis.

[15]  A. Bruckstein,et al.  K-SVD : An Algorithm for Designing of Overcomplete Dictionaries for Sparse Representation , 2005 .

[16]  Liyi Dai,et al.  Deep Dictionary Learning: A PARametric NETwork Approach , 2018, IEEE Transactions on Image Processing.

[17]  Yang Liu,et al.  Dictionary Learning Inspired Deep Network for Scene Recognition , 2018, AAAI.

[18]  Jun Guo,et al.  Synthesis K-SVD based analysis dictionary learning for pattern classification , 2017, Multimedia Tools and Applications.

[19]  Hamid Krim,et al.  Deep Transform and Metric Learning Network: Wedding Deep Dictionary Learning and Neural Networks , 2020, ArXiv.

[20]  M. Elad,et al.  $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation , 2006, IEEE Transactions on Signal Processing.

[21]  Liyi Dai,et al.  Analysis Dictionary Learning: an Efficient and Discriminative Solution , 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[22]  Pooja Gupta,et al.  DeConFuse: a deep convolutional transform-based unsupervised fusion framework , 2020, EURASIP J. Adv. Signal Process..

[23]  Émilie Chouzenoux,et al.  Variable Metric Forward–Backward Algorithm for Minimizing the Sum of a Differentiable Function and a Convex Function , 2013, Journal of Optimization Theory and Applications.

[24]  Jyoti Maggu,et al.  Unsupervised Deep Transform Learning , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[25]  I. M. Otivation Playing with Duality: An Overview of Recent Primal-Dual Approaches for Solving Large-Scale Optimization Problems , 2018 .

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

[27]  Antonio J. Plaza,et al.  Cloud Removal Based on Sparse Representation via Multitemporal Dictionary Learning , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[28]  Patrick L. Combettes,et al.  Proximal Splitting Methods in Signal Processing , 2009, Fixed-Point Algorithms for Inverse Problems in Science and Engineering.