Pruning Unrolled Networks (PUN) at Initialization for MRI Reconstruction Improves Generalization
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Image ReconstructionMRI ReconstructionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
End-to-end reconstruction meets data-driven regularization for inverse problems
We propose an unsupervised approach for learning end-to-end reconstruction operators for ill-posed inverse problems. The proposed method combines the classical variational framework with iterative unrolling, which essent…
Computational EfficiencyComputed Tomography (CT)Rolling Shutter CorrectionNaka-GS: A Bionics-inspired Dual-Branch Naka Correction and Progressive Point Pruning for Low-Light 3DGS
Low-light conditions severely hinder 3D restoration and reconstruction by degrading image visibility, introducing color distortions, and contaminating geometric priors for downstream optimization. We present NAKA-GS, a b…
3D ReconstructionUnrolled Reconstruction with Integrated Super-Resolution for Accelerated 3D LGE MRI
Accelerated 3D late gadolinium enhancement (LGE) MRI requires robust reconstruction methods to recover thin atrial structures from undersampled k-space data. While unrolled model-based networks effectively integrate phys…
Bridging The Gaps Between Token Pruning and Full Pre-training via Masked Fine-tuning
Despite the success of transformers on various computer vision tasks, they suffer from excessive memory and computational cost. Some works present dynamic vision transformers to accelerate inference by pruning redundant …
Pruning Neural Networks at Initialization: Why are We Missing the Mark?
Recent work has explored the possibility of pruning neural networks at initialization. We assess proposals for doing so: SNIP (Lee et al., 2019), GraSP (Wang et al., 2020), SynFlow (Tanaka et al., 2020), and magnitude pr…