Metraipolis › archive › dc_119c56f92fda

Beyond Sparsity: Weight Location and Network Context in Pruned MRI Reconstruction — arXiv:2609.31812

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.31812
License (as archived)
CC0-1.0
Archived
2026-10-07T23:55:02.020Z
SHA-256 of the archived text
adae2a7a2e421e0d147b5a5d1ebc67a5a1e6b97eb4dd0f2975dfc20a7d57e231
Stable URL of this page
https://metraipolis.com/documento/dc_119c56f92fda

How to cite

Beyond Sparsity: Weight Location and Network Context in Pruned MRI Reconstruction — arXiv:2609.31812 — arXiv (en), https://arxiv.org/abs/2609.31812 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_119c56f92fda (Metraipolis archive dc_119c56f92fda, sha256 adae2a7a2e421e0d147b5a5d1ebc67a5a1e6b97eb4dd0f2975dfc20a7d57e231)
BibTeX
@misc{dc119c56f92fda,
  title = {Beyond Sparsity: Weight Location and Network Context in Pruned MRI Reconstruction — arXiv:2609.31812},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31812},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_119c56f92fda; sha256 adae2a7a2e421e0d147b5a5d1ebc67a5a1e6b97eb4dd0f2975dfc20a7d57e231},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31812. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Pruning reduces the number of weights in magnetic resonance imaging (MRI) reconstruction networks. Equal sparsity, however, can retain weights with different computational roles and different compatibility with the trained network. We study these effects across 120 convolutional U-Net and vision transformer models using controlled edits evaluated before retraining. In U-Net, preserving high-resolution computation improves reconstruction at equal deletion counts across all tested sparsity levels. Equal-operation controls reveal additional sensitivity of the first convolution, which operation count alone cannot explain. In transformers, retained pretrained weight energy correlates with quality within sparsity levels, yet the same masks reverse their reconstruction ranking when the surrounding trained weights change. At 90\% sparsity, matching intermediate output scales largely removes a high-energy-mask penalty while retaining an advantage for the network's original mask. Thus sparsity alone does not characterize reconstruction quality: architecture-specific descriptors are informative, but mask quality can still depend on the surrounding trained network.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV).
Categorie arXiv: Image and Video Processing (eess.IV) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.31812 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T23:29:27.657Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).