Memory-efficient Learning for Large-scale Computational Imaging

2020/03/11 by Kellman, Michael, Zhang, Kevin, Tamir, Jon +3
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Signal Processing (eess.SP) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2003.05551

Abstract

Critical aspects of computational imaging systems, such as experimental design and image priors, can be optimized through deep networks formed by the unrolled iterations of classical model-based reconstructions (termed physics-based networks). However, for real-world large-scale inverse problems, computing gradients via backpropagation is infeasible due to memory limitations of graphics processing units. In this work, we propose a memory-efficient learning procedure that exploits the reversibility of the network's layers to enable data-driven design for large-scale computational imaging systems. We demonstrate our method on a small-scale compressed sensing example, as well as two large-scale real-world systems: multi-channel magnetic resonance imaging and super-resolution optical microscopy.

Related

• Memory-efficient Learning for Large-scale Computational Imaging -- NeurIPS deep inverse workshop
• Memory-efficient model-based deep learning with convergence and robustness guarantees
• Memory-efficient Learning for High-Dimensional MRI Reconstruction
• Memory-efficient deep end-to-end posterior network (DEEPEN) for inverse problems
• Deep Equilibrium Architectures for Inverse Problems in Imaging