Show simple item record

dc.contributor.authorXiao, Lei
dc.contributor.authorHeide, Felix
dc.contributor.authorHeidrich, Wolfgang
dc.contributor.authorSchölkopf, Bernhard
dc.contributor.authorHirsch, Michael
dc.date.accessioned2018-05-30T08:31:19Z
dc.date.available2017-12-28T07:32:12Z
dc.date.available2018-05-30T08:31:19Z
dc.date.issued2018-04-30
dc.identifier.citationXiao L, Heide F, Heidrich W, Schölkopf B, Hirsch M (2018) Discriminative Transfer Learning for General Image Restoration. IEEE Transactions on Image Processing 27: 4091–4104. Available: http://dx.doi.org/10.1109/TIP.2018.2831925.
dc.identifier.issn1057-7149
dc.identifier.issn1941-0042
dc.identifier.doi10.1109/TIP.2018.2831925
dc.identifier.urihttp://hdl.handle.net/10754/626486
dc.description.abstractRecently, several discriminative learning approaches have been proposed for effective image restoration, achieving convincing trade-off between image quality and computational efficiency. However, these methods require separate training for each restoration task (e.g., denoising, deblurring, demosaicing) and problem condition (e.g., noise level of input images). This makes it time-consuming and difficult to encompass all tasks and conditions during training. In this paper, we propose a discriminative transfer learning method that incorporates formal proximal optimization and discriminative learning for general image restoration. The method requires a single-pass discriminative training and allows for reuse across various problems and conditions while achieving an efficiency comparable to previous discriminative approaches. Furthermore, after being trained, our model can be easily transferred to new likelihood terms to solve untrained tasks, or be combined with existing priors to further improve image restoration quality.
dc.description.sponsorshipThis work was in part supported by King Abdullah University of Science and Technology under individual baseline funding. The associate editor coordinating the review of this manuscript and approving it for publication was Prof. Weisi Lin.
dc.language.isoen
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)
dc.relation.urlhttps://ieeexplore.ieee.org/document/8352765/
dc.rights(c) 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.
dc.subjectdiscriminative learning
dc.subjectImage restoration
dc.subjectproximal optimization
dc.titleDiscriminative Transfer Learning for General Image Restoration
dc.typeArticle
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.departmentComputer Science Program
dc.contributor.departmentVisual Computing Center (VCC)
dc.identifier.journalIEEE Transactions on Image Processing
dc.eprint.versionPost-print
dc.contributor.institutionDepartment of Computer Science at University of British Columbia.
dc.contributor.institutionDepartment of Electrical Engineering at Stanford University.
dc.contributor.institutionMax Planck Institute for Intelligent Systems.
dc.identifier.arxividarXiv:1703.09245
kaust.personHeidrich, Wolfgang
refterms.dateFOA2018-06-14T02:15:35Z


Files in this item

Thumbnail
Name:
Xiao2018TransferLearning.pdf
Size:
23.02Mb
Format:
PDF
Description:
Accepted Manuscript

This item appears in the following Collection(s)

Show simple item record

VersionItemEditorDateSummary

*Selected version