Show simple item record

dc.contributor.authorAffara, Lama Ahmed
dc.contributor.authorGhanem, Bernard
dc.contributor.authorWonka, Peter
dc.date.accessioned2018-04-16T11:27:44Z
dc.date.available2018-04-16T11:27:44Z
dc.date.issued2018-04-08
dc.identifier.urihttp://hdl.handle.net/10754/627542
dc.description.abstractConvolutional Sparse Coding (CSC) is a well-established image representation model especially suited for image restoration tasks. In this work, we extend the applicability of this model by proposing a supervised approach to convolutional sparse coding, which aims at learning discriminative dictionaries instead of purely reconstructive ones. We incorporate a supervised regularization term into the traditional unsupervised CSC objective to encourage the final dictionary elements to be discriminative. Experimental results show that using supervised convolutional learning results in two key advantages. First, we learn more semantically relevant filters in the dictionary and second, we achieve improved image reconstruction on unseen data.
dc.publisherarXiv
dc.relation.urlhttp://arxiv.org/abs/1804.02678v1
dc.relation.urlhttp://arxiv.org/pdf/1804.02678v1
dc.rightsArchived with thanks to arXiv
dc.titleSupervised Convolutional Sparse Coding
dc.typePreprint
dc.contributor.departmentComputer Science Program
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.departmentElectrical Engineering Program
dc.contributor.departmentVisual Computing Center (VCC)
dc.eprint.versionPre-print
dc.identifier.arxividarXiv:1804.02678
kaust.personAffara, Lama Ahmed
kaust.personGhanem, Bernard
kaust.personWonka, Peter
dc.versionv1
refterms.dateFOA2018-06-14T04:21:41Z


Files in this item

Thumbnail
Name:
1804.02678v1.pdf
Size:
1.141Mb
Format:
PDF
Description:
Preprint

This item appears in the following Collection(s)

Show simple item record