Deep Equilibrium Architectures for Inverse Problems in Imaging
| Autor: | Rebecca Willett, Davis Gilton, Gregory Ongie |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Infinite number Computer science Computation Noise reduction Computer Vision and Pattern Recognition (cs.CV) 010401 analytical chemistry Image and Video Processing (eess.IV) Computer Science - Computer Vision and Pattern Recognition 020206 networking & telecommunications 02 engineering and technology Iterative reconstruction Inverse problem Electrical Engineering and Systems Science - Image and Video Processing 01 natural sciences 0104 chemical sciences Computer Science Applications Computational Mathematics Signal Processing Convergence (routing) 0202 electrical engineering electronic engineering information engineering FOS: Electrical engineering electronic engineering information engineering Deep neural networks Algorithm Computational budget |
| DOI: | 10.48550/arxiv.2102.07944 |
| Popis: | Recent efforts on solving inverse problems in imaging via deep neural networks use architectures inspired by a fixed number of iterations of an optimization method. The number of iterations is typically quite small due to difficulties in training networks corresponding to more iterations; the resulting solvers cannot be run for more iterations at test time without incurring significant errors. This paper describes an alternative approach corresponding to an infinite number of iterations, yielding a consistent improvement in reconstruction accuracy above state-of-the-art alternatives and where the computational budget can be selected at test time to optimize context-dependent trade-offs between accuracy and computation. The proposed approach leverages ideas from Deep Equilibrium Models, where the fixed-point iteration is constructed to incorporate a known forward model and insights from classical optimization-based reconstruction methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|