mlsanityData to 14 Oct 2026

Awaken, Then Scale: Tiny Adaptation for MRI Reconstruction

arXiv 2609.31813 ↗First posted 25 Sep 2026eess.IV cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Dormant Awakening (DA) specializes a magnetic resonance imaging (MRI) reconstruction model by fitting a small set of zero weights to one labeled slice. Across fourteen U-shaped convolutional network (U-Net) and vision transformer (ViT) sources, fitting 1,004 or 10,560 weights gives mean peak signal-to-noise ratio (PSNR) gains of .430 and .509 dB. We analyze how scaling the fitted output correction changes evaluation PSNR, then use the calibration correction size to cap changes on new images. The cap bounds changes in root mean squared error (RMSE) relative to the source without an evaluation reference. At 10% adaptation budget, we compare fixed halving and dynamic capping for DA, unrestricted sparse adaptation and low-rank adaptation (LoRA). The controls increase both measured calibration-evaluation correlations across all six tested architecture-adapter settings. Experiments concern one constructed fastMRI-to-M4Raw shift with fixed source checkpoints and participant panels.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 30 references that are in the map. First posted on arXiv 25 Sep 2026.

Builds on

20 of 30 references.

References · 20

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2021Convex optimizationcited by 2,515
  4. 2017PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruningcited by 898
  5. 2018SNIP: Single-shot Network Pruning based on Connection Sensitivitycited by 812
  6. 2021Robust fine-tuning of zero-shot modelscited by 797
  7. 2019Rigging the Lottery: Making All Tickets Winnerscited by 495
  8. 2018fastMRI: An Open Dataset and Benchmarks for Accelerated MRIcited by 470
  9. 2020Parameter-Efficient Transfer Learning with Diff Pruningcited by 352
  10. 2023Parameter-Efficient Fine-Tuning without Introducing New Latencycited by 59
  11. 2021Zero-Shot Self-Supervised Learning for MRI Reconstructioncited by 54
  12. 2024RoSA: Accurate Parameter-Efficient Fine-Tuning via Robust Adaptationcited by 48
8 more
  1. 2022Test-Time Training Can Close the Natural Distribution Shift Performance Gap in Deep Learning Based Compressed Sensingcited by 37
  2. 2024Sparse High Rank Adapterscited by 17
  3. 2024SAFT: Towards Out-of-Distribution Generalization in Fine-Tuningcited by 12
  4. 2022PAC-Net: A Model Pruning Approach to Inductive Transfer Learningcited by 6
  5. 2023Continual Domain Adaptation through Pruning-aided Domain-specific Weight Modulationcited by 3
  6. 2024Pruning Unrolled Networks (PUN) at Initialization for MRI Reconstruction Improves Generalizationcited by 3
  7. 2023FAM: fast adaptive federated meta-learningcited by 1
  8. 2025D2SA: Dual-Stage Distribution and Slice Adaptation for Efficient Test-Time Adaptation in MRI Reconstructioncited by 1

Built on by

Not cited yet.