Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/159943
Full metadata record
DC FieldValueLanguage
dc.contributor.authorZeng, Yijieen_US
dc.contributor.authorChen, Jichaoen_US
dc.contributor.authorHuang, Guang-Binen_US
dc.date.accessioned2022-07-06T03:00:20Z-
dc.date.available2022-07-06T03:00:20Z-
dc.date.issued2019-
dc.identifier.citationZeng, Y., Chen, J. & Huang, G. (2019). Slice-based online convolutional dictionary learning. IEEE Transactions On Cybernetics, 51(10), 5116-5129. https://dx.doi.org/10.1109/TCYB.2019.2931914en_US
dc.identifier.issn2168-2267en_US
dc.identifier.urihttps://hdl.handle.net/10356/159943-
dc.description.abstractConvolutional dictionary learning (CDL) aims to learn a structured and shift-invariant dictionary to decompose signals into sparse representations. While yielding superior results compared to traditional sparse coding methods on various signal and image processing tasks, most CDL methods have difficulties handling large data, because they have to process all images in the dataset in a single pass. Therefore, recent research has focused on online CDL (OCDL) which updates the dictionary with sequentially incoming signals. In this article, a novel OCDL algorithm is proposed based on a local, slice-based representation of sparse codes. Such representation has been found useful in batch CDL problems, where the convolutional sparse coding and dictionary learning problem could be handled in a local way similar to traditional sparse coding problems, but it has never been explored under online scenarios before. We show, in this article, that the proposed algorithm is a natural extension of the traditional patch-based online dictionary learning algorithm, and the dictionary is updated in a similar memory efficient way too. On the other hand, it can be viewed as an improvement of existing second-order OCDL algorithms. Theoretical analysis shows that our algorithm converges and has lower time complexity than existing counterpart that yields exactly the same output. Extensive experiments are performed on various benchmarking datasets, which show that our algorithm outperforms state-of-the-art batch and OCDL algorithms in terms of reconstruction objectives.en_US
dc.language.isoenen_US
dc.relation.ispartofIEEE Transactions on Cyberneticsen_US
dc.rights© 2019 IEEE. All rights reserved.en_US
dc.subjectEngineering::Electrical and electronic engineeringen_US
dc.titleSlice-based online convolutional dictionary learningen_US
dc.typeJournal Articleen
dc.contributor.schoolSchool of Electrical and Electronic Engineeringen_US
dc.identifier.doi10.1109/TCYB.2019.2931914-
dc.identifier.pmid31443059-
dc.identifier.scopus2-s2.0-85117402247-
dc.identifier.issue10en_US
dc.identifier.volume51en_US
dc.identifier.spage5116en_US
dc.identifier.epage5129en_US
dc.subject.keywordsConvolutional Sparse Codingen_US
dc.subject.keywordsDictionary Learningen_US
item.grantfulltextnone-
item.fulltextNo Fulltext-
Appears in Collections:EEE Journal Articles

SCOPUSTM   
Citations 50

4
Updated on Sep 28, 2023

Web of ScienceTM
Citations 50

4
Updated on Sep 22, 2023

Page view(s)

38
Updated on Sep 27, 2023

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.