Projecting on to the Multi-Layer Convolutional Sparse Coding Model

The recently proposed Multi-Layer Convolutional Sparse Coding (ML-CSC) model, consisting of a cascade of convolutional sparse layers, provides a new interpretation of Convolutional Neural Networks (CNNs). Under this framework, the forward pass in a CNN is equivalent to an algorithm that estimates ne...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) S. 6757 - 6761
Hauptverfasser: Sulam, Jeremias, Papyant, Vardan, Romano, Yaniv, Elad, Michael
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.04.2018
Schlagworte:
ISSN:2379-190X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract The recently proposed Multi-Layer Convolutional Sparse Coding (ML-CSC) model, consisting of a cascade of convolutional sparse layers, provides a new interpretation of Convolutional Neural Networks (CNNs). Under this framework, the forward pass in a CNN is equivalent to an algorithm that estimates nested sparse representation vectors from a given input signal. Despite having served as a pivotal connection between CNNs and sparse modeling, it is still unclear how to develop pursuit algorithms that serve this model exactly. In this work, we propose a new pursuit formulation by adopting a projection approach. We provide new and improved bounds on the stability of the resulting convolutional sparse representations, and we propose a multi-layer projection algorithm to retrieve them. We demonstrate this algorithm numerically, showing that it is superior to the Layered Basis Pursuit alternative in retrieving the representations of signals belonging to the ML-CSC model.
AbstractList The recently proposed Multi-Layer Convolutional Sparse Coding (ML-CSC) model, consisting of a cascade of convolutional sparse layers, provides a new interpretation of Convolutional Neural Networks (CNNs). Under this framework, the forward pass in a CNN is equivalent to an algorithm that estimates nested sparse representation vectors from a given input signal. Despite having served as a pivotal connection between CNNs and sparse modeling, it is still unclear how to develop pursuit algorithms that serve this model exactly. In this work, we propose a new pursuit formulation by adopting a projection approach. We provide new and improved bounds on the stability of the resulting convolutional sparse representations, and we propose a multi-layer projection algorithm to retrieve them. We demonstrate this algorithm numerically, showing that it is superior to the Layered Basis Pursuit alternative in retrieving the representations of signals belonging to the ML-CSC model.
Author Elad, Michael
Romano, Yaniv
Sulam, Jeremias
Papyant, Vardan
Author_xml – sequence: 1
  givenname: Jeremias
  surname: Sulam
  fullname: Sulam, Jeremias
  organization: Computer Science Department
– sequence: 2
  givenname: Vardan
  surname: Papyant
  fullname: Papyant, Vardan
  organization: Computer Science Department
– sequence: 3
  givenname: Yaniv
  surname: Romano
  fullname: Romano, Yaniv
  organization: Electrical Engineering Department, Technion - Israel Institute of Technology
– sequence: 4
  givenname: Michael
  surname: Elad
  fullname: Elad, Michael
  organization: Computer Science Department
BookMark eNotj81Kw0AcxFdRsNY8QS_7Aon7nd2jBr8gxUJ68FY2m390S9wtyVbo2xuxp4GB-c3MLboKMQBCK0oKSom5f6semmZTMEJ1oYViUrILlJlSU8m1EkpqfYkWjJcmp4Z83KBsmvaEEKa0KKVaoMfNGPfgkg-fOAacIk5fgNfHIfm8ticYcRXDTxyOycdgB9wc7DjBbHZ_iXXsYLhD170dJsjOukTb56dt9ZrX7y_zvjr3hqQcDGs7Csz0Svd2bmfCMcJBu9Y6Z1pORU8YES10YCQBQ62DUvWWCdkpDXyJVv9YDwC7w-i_7XjanU_zX6lgTac
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/ICASSP.2018.8462552
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISBN 9781538646588
1538646587
EISSN 2379-190X
EndPage 6761
ExternalDocumentID 8462552
Genre orig-research
GroupedDBID 23M
29P
6IE
6IF
6IH
6IK
6IL
6IM
6IN
AAJGR
AAWTH
ABLEC
ACGFS
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
IPLJI
M43
OCL
RIE
RIL
RIO
RNS
ID FETCH-LOGICAL-i90t-e92bd1e29f68fa84724c203e8cbacc9b314f0204bede950e91ace76fa245d68e3
IEDL.DBID RIE
IngestDate Wed Aug 27 02:55:02 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i90t-e92bd1e29f68fa84724c203e8cbacc9b314f0204bede950e91ace76fa245d68e3
PageCount 5
ParticipantIDs ieee_primary_8462552
PublicationCentury 2000
PublicationDate 2018-April
PublicationDateYYYYMMDD 2018-04-01
PublicationDate_xml – month: 04
  year: 2018
  text: 2018-April
PublicationDecade 2010
PublicationTitle 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
PublicationTitleAbbrev ICASSP
PublicationYear 2018
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0002684756
ssj0008748
Score 2.0473392
Snippet The recently proposed Multi-Layer Convolutional Sparse Coding (ML-CSC) model, consisting of a cascade of convolutional sparse layers, provides a new...
SourceID ieee
SourceType Publisher
StartPage 6757
SubjectTerms Atomic measurements
Coherence
Convolution
Convolutional codes
Convolutional Neural Networks
Convolutional Sparse Coding
Dictionaries
Encoding
Multilayer Pursuit
Stability analysis
Stability Guarantees
Title Projecting on to the Multi-Layer Convolutional Sparse Coding Model
URI https://ieeexplore.ieee.org/document/8462552
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07a8MwEBZp6NAufSSlbzR0rBPb8kMa29DQQgiGZMgW9DhBINghdfL7e5JN2kKXLsbWcJiT0d13vu87Qp6YMhphRxiAEQhQLMIdLiK8pDa0gMCZWa-uP8mnU75YiKJDng9cGADwzWcwcLf-X76p9M6VyoYYKzEDxgP3KM-zhqt1qKc41RKvZN6ewjxPeKsyFIVi-DF6mc0K18rFB62ZX_NUfDgZn_3vRc5J_5uXR4tDxLkgHSgvyekPScEeeS2a0go-0KqkdUUxw6OeZhtMJObXFG3t2-9Nrulsg8gWcNFZpG4y2rpP5uO3-eg9aOckBCsR1gGIWJkIYmEzbiV6IU50HDLgWkmthWJRYh0FVoEBkYYgIqkhz6yMk9RkHNgV6ZZVCdeEguLcqMg0wI8znscS8xunWmgQWLAb0nPOWG4aJYxl64fbv5fvyInzd9Pnck-69XYHD-RY7-vV5_bRb98XNcyZpA
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEB5KFdSLj1Z8uwePps07u0ctlhZjCbSH3kqyOwuFkpSa9vc7m4Sq4MVLSPYwhNmwM99kvm8AnrxMSYIdtoVKEEDRBHe4cOgSaFsjAWdPV-r6cTSZ8PlcJC143nNhELFqPsOeua3-5atCbk2prE-xkjJgOnAPAt937Zqtta-oGN2SSsu8OYd55PNGZ8ixRX88eJlOE9PMxXuNoV8TVaqAMjz936ucQfebmceSfcw5hxbmF3DyQ1SwA69JXVyhB1bkrCwY5XisItpacUoZNiNbu-aLS1dsuiZsi7RoLDIzG23VhdnwbTYYWc2kBGsp7NJC4WbKQVfokOuUvOD60rU95DJLpRSZ5_jakGAzVCgCG4WTSoxCnbp-oEKO3iW08yLHK2CYca4yR9XQj3s8clPKcIxuoSJo4V1Dxzhjsa61MBaNH27-Xn6Eo9HsI17E48n7LRwb39ddL3fQLjdbvIdDuSuXn5uHaiu_AGXRnOs
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2018+IEEE+International+Conference+on+Acoustics%2C+Speech+and+Signal+Processing+%28ICASSP%29&rft.atitle=Projecting+on+to+the+Multi-Layer+Convolutional+Sparse+Coding+Model&rft.au=Sulam%2C+Jeremias&rft.au=Papyant%2C+Vardan&rft.au=Romano%2C+Yaniv&rft.au=Elad%2C+Michael&rft.date=2018-04-01&rft.pub=IEEE&rft.eissn=2379-190X&rft.spage=6757&rft.epage=6761&rft_id=info:doi/10.1109%2FICASSP.2018.8462552&rft.externalDocID=8462552