A alpha-Divergence-Based Approach for Robust Dictionary Learning
AuthorIqbal, A; Seghouane, A-K
Source TitleIEEE Transactions on Image Processing
PublisherInstitute of Electrical and Electronics Engineers
AffiliationElectrical and Electronic Engineering
School of Mathematics and Statistics
Document TypeJournal Article
CitationsIqbal, A. & Seghouane, A. -K. (2019). A alpha-Divergence-Based Approach for Robust Dictionary Learning. IEEE Transactions on Image Processing, 28 (11), https://doi.org/10.1109/TIP.2019.2922074.
Access StatusThis item is embargoed and will be available on 2021-11-01
ARC Grant codeARC/FT130101394
In this paper, a robust sequential dictionary learning (DL) algorithm is presented. The proposed algorithm is motivated from the maximum likelihood perspective on dictionary learning and its link to the minimization of the Kullback-Leibler divergence. It is obtained by using a robust loss function in the data fidelity term of the DL objective instead of the usual quadratic loss. The proposed robust loss function is derived from the α-divergence as an alternative to the Kullback-Leibler divergence, which leads to a quadratic loss. Compared to other robust approaches, the proposed loss has the advantage of belonging to class of redescending M-estimators, guaranteeing inference stability from large deviations from the Gaussian nominal noise model. The algorithm is obtained by solving a sequence of penalized rank-1 matrix approximation problems, where the ℓ 1 -norm is introduced as a penalty promoting sparsity and then using a block coordinate descent approach to estimate the unknowns. Performance comparison with similar robust DL algorithms on digit recognition, background removal, and gray-scale image denoising is performed highlighting efficacy of the proposed algorithm.
- Click on "Export Reference in RIS Format" and choose "open with... Endnote".
- Click on "Export Reference in RIS Format". Login to Refworks, go to References => Import References