A multilayered convolutional sparse coding framework for modeling of pooling operation of convolution neural networks

Convolutional Sparse Coding (CSC) framework has been proposed recently to explain relation between Convolutional Neural Networks (CNNs) and sparse coding theory. The multilayered version of CSC(ML-CSC) is shown to be connected to forward pass of CNNs and dictionary learning and sparse coding algorit...

Full description

Bibliographic Details
Main Authors: , Abdul Wahid, Khan, Adnan Umar, , Mukhtarullah, Khan, Sheroz, Shah, Jawad
Format: Proceeding Paper
Language:English
English
Published: IEEE 2019
Subjects:
Online Access:http://irep.iium.edu.my/80454/
http://irep.iium.edu.my/80454/1/80454%20A%20Multilayered%20Convolutional%20Sparse%20Coding%20Framework.pdf
http://irep.iium.edu.my/80454/2/80454%20A%20Multilayered%20Convolutional%20Sparse%20Coding%20Framework%20SCOPUS.pdf
_version_ 1848788961744388096
author , Abdul Wahid
Khan, Adnan Umar
, Mukhtarullah
Khan, Sheroz
Shah, Jawad
author_facet , Abdul Wahid
Khan, Adnan Umar
, Mukhtarullah
Khan, Sheroz
Shah, Jawad
author_sort , Abdul Wahid
building IIUM Repository
collection Online Access
description Convolutional Sparse Coding (CSC) framework has been proposed recently to explain relation between Convolutional Neural Networks (CNNs) and sparse coding theory. The multilayered version of CSC(ML-CSC) is shown to be connected to forward pass of CNNs and dictionary learning and sparse coding algorithms of this model are analyzed for solving classification and inverse problems in image processing. However open problems like effect of pooling operations, batch normalization and dictionary learning in context of ML-CSC framework remain challenging issues especially in implementation scenarios. In this work we implement the framework for multi layered version of CSC with incorporation of pooling operations applied on real images and analyze the performance of resulting model. We demonstrate that with optimal parameters selected for sparsity of feature maps, the pooling operation (here max pooling) when used layered wise in ML-CSC framework improves the effective dictionaries and resulting feature maps, which in turn improves the reconstruction accuracy of images after multilayered implementation.
first_indexed 2025-11-14T17:49:09Z
format Proceeding Paper
id iium-80454
institution International Islamic University Malaysia
institution_category Local University
language English
English
last_indexed 2025-11-14T17:49:09Z
publishDate 2019
publisher IEEE
recordtype eprints
repository_type Digital Repository
spelling iium-804542020-07-13T06:50:30Z http://irep.iium.edu.my/80454/ A multilayered convolutional sparse coding framework for modeling of pooling operation of convolution neural networks , Abdul Wahid Khan, Adnan Umar , Mukhtarullah Khan, Sheroz Shah, Jawad T Technology (General) Convolutional Sparse Coding (CSC) framework has been proposed recently to explain relation between Convolutional Neural Networks (CNNs) and sparse coding theory. The multilayered version of CSC(ML-CSC) is shown to be connected to forward pass of CNNs and dictionary learning and sparse coding algorithms of this model are analyzed for solving classification and inverse problems in image processing. However open problems like effect of pooling operations, batch normalization and dictionary learning in context of ML-CSC framework remain challenging issues especially in implementation scenarios. In this work we implement the framework for multi layered version of CSC with incorporation of pooling operations applied on real images and analyze the performance of resulting model. We demonstrate that with optimal parameters selected for sparsity of feature maps, the pooling operation (here max pooling) when used layered wise in ML-CSC framework improves the effective dictionaries and resulting feature maps, which in turn improves the reconstruction accuracy of images after multilayered implementation. IEEE 2019 Proceeding Paper PeerReviewed application/pdf en http://irep.iium.edu.my/80454/1/80454%20A%20Multilayered%20Convolutional%20Sparse%20Coding%20Framework.pdf application/pdf en http://irep.iium.edu.my/80454/2/80454%20A%20Multilayered%20Convolutional%20Sparse%20Coding%20Framework%20SCOPUS.pdf , Abdul Wahid and Khan, Adnan Umar and , Mukhtarullah and Khan, Sheroz and Shah, Jawad (2019) A multilayered convolutional sparse coding framework for modeling of pooling operation of convolution neural networks. In: 2019 IEEE 6th International Conference on Smart Instrumentation, Measurement and Applications (ICSIMA 2019), 27 - 29 Aug 2019, Kuala Lumpur, Malaysia. https://ieeexplore.ieee.org/document/9057334 10.1109/ICSIMA47653.2019.9057334
spellingShingle T Technology (General)
, Abdul Wahid
Khan, Adnan Umar
, Mukhtarullah
Khan, Sheroz
Shah, Jawad
A multilayered convolutional sparse coding framework for modeling of pooling operation of convolution neural networks
title A multilayered convolutional sparse coding framework for modeling of pooling operation of convolution neural networks
title_full A multilayered convolutional sparse coding framework for modeling of pooling operation of convolution neural networks
title_fullStr A multilayered convolutional sparse coding framework for modeling of pooling operation of convolution neural networks
title_full_unstemmed A multilayered convolutional sparse coding framework for modeling of pooling operation of convolution neural networks
title_short A multilayered convolutional sparse coding framework for modeling of pooling operation of convolution neural networks
title_sort multilayered convolutional sparse coding framework for modeling of pooling operation of convolution neural networks
topic T Technology (General)
url http://irep.iium.edu.my/80454/
http://irep.iium.edu.my/80454/
http://irep.iium.edu.my/80454/
http://irep.iium.edu.my/80454/1/80454%20A%20Multilayered%20Convolutional%20Sparse%20Coding%20Framework.pdf
http://irep.iium.edu.my/80454/2/80454%20A%20Multilayered%20Convolutional%20Sparse%20Coding%20Framework%20SCOPUS.pdf