Principal Component Wavelet Networks for Solving Linear Inverse Problems

In this paper we propose a novel learning-based wavelet transform and demonstrate its utility as a representation in solving a number of linear inverse problems—these are asymmetric problems, where the forward problem is easy to solve, but the inverse is difficult and often ill-posed. The wavelet de...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Symmetry (Basel) Ročník 13; číslo 6; s. 1083
Hlavní autori: Tiddeman, Bernard, Ghahremani, Morteza
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Basel MDPI AG 01.06.2021
Predmet:
Algorithms
Artificial neural networks
Convolution
Decomposition
Deep learning
Discrete Wavelet Transform
Electromagnetic wave filters
Filter banks
Forward problem
Generative adversarial networks
Inverse problems
Neural networks
Noise reduction
Principal components analysis
Subtraction
Success
Wavelet transforms
ISSN:2073-8994, 2073-8994
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:In this paper we propose a novel learning-based wavelet transform and demonstrate its utility as a representation in solving a number of linear inverse problems—these are asymmetric problems, where the forward problem is easy to solve, but the inverse is difficult and often ill-posed. The wavelet decomposition is comprised of the application of an invertible 2D wavelet filter-bank comprising symmetric and anti-symmetric filters, in combination with a set of 1×1 convolution filters learnt from Principal Component Analysis (PCA). The 1×1 filters are needed to control the size of the decomposition. We show that the application of PCA across wavelet subbands in this way produces an architecture equivalent to a separable Convolutional Neural Network (CNN), with the principal components forming the 1×1 filters and the subtraction of the mean forming the bias terms. The use of an invertible filter bank and (approximately) invertible PCA allows us to create a deep autoencoder very simply, and avoids issues of overfitting. We investigate the construction and learning of such networks, and their application to linear inverse problems via the Alternating Direction of Multipliers Method (ADMM). We use our network as a drop-in replacement for traditional discrete wavelet transform, using wavelet shrinkage as the projection operator. The results show good potential on a number of inverse problems such as compressive sensing, in-painting, denoising and super-resolution, and significantly close the performance gap with Generative Adversarial Network (GAN)-based methods.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2073-8994
2073-8994
DOI:10.3390/sym13061083