Pruning Unrolled Networks (PUN) at Initialization for MRI Reconstruction Improves Generalization

TL;DR

This paper introduces a pruning method at initialization for unrolled MRI reconstruction networks, which enhances their robustness and generalization across different experimental conditions and distribution shifts.

Contribution

The study proposes PUN, a novel pruning approach at initialization specifically designed for unrolled networks in MRI reconstruction, improving robustness and generalization.

Findings

PUN improves generalization across various experimental settings.

PUN offers slight performance gains on in-distribution data.

Pruning at initialization enhances robustness to distribution shifts.

Abstract

Deep learning methods are highly effective for many image reconstruction tasks. However, the performance of supervised learned models can degrade when applied to distinct experimental settings at test time or in the presence of distribution shifts. In this study, we demonstrate that pruning deep image reconstruction networks at training time can improve their robustness to distribution shifts. In particular, we consider unrolled reconstruction architectures for accelerated magnetic resonance imaging and introduce a method for pruning unrolled networks (PUN) at initialization. Our experiments demonstrate that when compared to traditional dense networks, PUN offers improved generalization across a variety of experimental settings and even slight performance gains on in-distribution data.