Bayesian deep matrix factorization network for multiple images denoising. (March 2020)

• Record Type: Journal Article
• Authors: Xu, Shuang; Zhang, Chunxia; Zhang, Jiangshe
• Is Part Of: Neural networks. Volume 123(2020)
• Page Start: 420
• Page End: 428
• Publication Date: 2020-03
• Subjects: Matrix factorization -- Bayesian neural networks -- Variational Bayes; Neural computers -- Periodicals; Neural networks (Computer science) -- Periodicals; Neural networks (Neurobiology) -- Periodicals; Nervous System -- Periodicals; Ordinateurs neuronaux -- Périodiques; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux neuronaux (Neurobiologie) -- Périodiques; Neural computers; Neural networks (Computer science); Neural networks (Neurobiology); Periodicals; 006.32
• DOI: 10.1016/j.neunet.2019.12.023
• Languages: English
• ISSNs: 0893-6080

Abstract

Abstract: This paper aims at proposing a robust and fast low rank matrix factorization model for multiple images denoising. To this end, a novel model, Bayesian deep matrix factorization network (BDMF), is presented, where a deep neural network (DNN) is designed to model the low rank components and the model is optimized via stochastic gradient variational Bayes. By the virtue of deep learning and Bayesian modeling, BDMF makes significant improvement on synthetic experiments and real-world tasks (including shadow removal and hyperspectral image denoising), compared with existing state-of-the-art models.