Journal
IEEE TRANSACTIONS ON CYBERNETICS
Volume 51, Issue 10, Pages 5116-5129Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCYB.2019.2931914
Keywords
Dictionaries; Machine learning; Convolution; Task analysis; Convolutional codes; Time complexity; Image coding; Convolutional sparse coding (CSC); dictionary learning; local processing; online learning
Ask authors/readers for more resources
The article introduces a novel online CDL algorithm based on a local, slice-based representation that is efficient in handling large datasets and achieving superior performance. Theoretical analysis and experiments demonstrate that the algorithm has lower time complexity and better reconstruction objectives compared to existing methods.
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available