Parseval Convolution Operators and Neural Networks
Unser, Michael, Ducotterd, Stanislas
We first establish a kernel theorem that characterizes all linear shift-invariant (LSI) operators acting on discrete multicomponent signals. This result naturally leads to the identification of the Parseval convolution operators as the class of energy-preserving filterbanks. We then present a constructive approach for the design/specification of such filterbanks via the chaining of elementary Parseval modules, each of which being parameterized by an orthogonal matrix or a 1-tight frame. Our analysis is complemented with explicit formulas for the Lipschitz constant of all the components of a convolutional neural network (CNN), which gives us a handle on their stability. Finally, we demonstrate the usage of those tools with the design of a CNN-based algorithm for the iterative reconstruction of biomedical images. Our algorithm falls within the plug-and-play framework for the resolution of inverse problems. It yields better-quality results than the sparsity-based methods used in compressed sensing, while offering essentially the same convergence and robustness guarantees.
Aug-19-2024
- Country:
- North America > United States
- Washington > King County
- Seattle (0.04)
- Pennsylvania > Philadelphia County
- Philadelphia (0.04)
- Massachusetts > Norfolk County
- Wellesley (0.04)
- Hawaii > Honolulu County
- Honolulu (0.04)
- California > San Diego County
- San Diego (0.04)
- Washington > King County
- Europe
- United Kingdom > England
- Cambridgeshire > Cambridge (0.14)
- Switzerland > Vaud
- Lausanne (0.04)
- France > Île-de-France
- United Kingdom > England
- North America > United States
- Genre:
- Research Report (0.50)
- Industry:
- Health & Medicine (0.68)
- Technology: