Please use this identifier to cite or link to this item:
https://hdl.handle.net/10356/159943
Title: | Slice-based online convolutional dictionary learning | Authors: | Zeng, Yijie Chen, Jichao Huang, Guang-Bin |
Keywords: | Engineering::Electrical and electronic engineering | Issue Date: | 2019 | Source: | Zeng, 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.2019.2931914 | Journal: | IEEE Transactions on Cybernetics | Abstract: | Convolutional 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. | URI: | https://hdl.handle.net/10356/159943 | ISSN: | 2168-2267 | DOI: | 10.1109/TCYB.2019.2931914 | Schools: | School of Electrical and Electronic Engineering | Rights: | © 2019 IEEE. All rights reserved. | Fulltext Permission: | none | Fulltext Availability: | No Fulltext |
Appears in Collections: | EEE Journal Articles |
SCOPUSTM
Citations
50
3
Updated on Jun 3, 2023
Web of ScienceTM
Citations
50
4
Updated on Jun 6, 2023
Page view(s)
29
Updated on Jun 8, 2023
Google ScholarTM
Check
Altmetric
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.