paper-with-me

Papers

SubZero: Subspace Zero-Shot MRI Reconstruction

2023-11-28 · Heng Yu, Yamin Arefeen, Berkin Bilgic

Recently introduced zero-shot self-supervised learning (ZS-SSL) has shown potential in accelerated MRI in a scan-specific scenario, which enabled high-quality reconstructions without access to a large training dataset. ZS-SSL has been further combined with the subspace model to accelerate 2D T2-shuffling acquisitions. In this work, we propose a parallel network framework and introduce an attention mechanism to improve subspace-based zero-shot self-supervised learning and enable higher acceleration factors. We name our method SubZero and demonstrate that it can achieve improved performance compared with current methods in T1 and T2 mapping acquisitions.

📄 PDF Abstract BibTeX arXiv:2311.17251

Code (1)

heng14/subzero 공식 구현 tf

Tasks

MRI ReconstructionSelf-Supervised Learning

Similar Papers 제목 키워드 기반

Zeroth-Order Fine-Tuning of LLMs in Random Subspaces

2024-10-11 · Ziming Yu, Pan Zhou, Sike Wang, Jia Li 외

Fine-tuning Large Language Models (LLMs) has proven effective for a variety of downstream tasks. However, as LLMs grow in size, the memory demands for backpropagation become increasingly prohibitive. Zeroth-order (ZO) op…

Language ModelingLanguage Modelling

SubZeroCore: A Submodular Approach with Zero Training for Coreset Selection

2025-09-26 · Brian B. Moser, Tobias C. Nauen, Arundhati S. Shanbhag, Federico Raue 외 arxiv

The goal of coreset selection is to identify representative subsets of datasets for efficient model training. Yet, existing approaches paradoxically require expensive training-based signals, e.g., gradients, decision bou…

SubZero: Composing Subject, Style, and Action via Zero-Shot Personalization

2025-02-27 · Shubhankar Borse, Kartikeya Bhardwaj, Mohammad Reza Karimi Dastjerdi, Hyojin Park 외

Diffusion models are increasingly popular for generative tasks, including personalized composition of subjects and styles. While diffusion models can generate user-specified subjects performing text-guided actions in cus…

Denoising

Zero-DeepSub: Zero-Shot Deep Subspace Reconstruction for Rapid Multiparametric Quantitative MRI Using 3D-QALAS

2023-07-04 · Yohan Jun, Yamin Arefeen, Jaejin Cho, Shohei Fujita 외

Purpose: To develop and evaluate methods for 1) reconstructing 3D-quantification using an interleaved Look-Locker acquisition sequence with T2 preparation pulse (3D-QALAS) time-series images using a low-rank subspace met…

Quantitative MRI

NLCG-Net: A Model-Based Zero-Shot Learning Framework for Undersampled Quantitative MRI Reconstruction

2024-01-22 · Xinrui Jiang, Yohan Jun, Jaejin Cho, Mengze Gao 외

Typical quantitative MRI (qMRI) methods estimate parameter maps after image reconstructing, which is prone to biases and error propagation. We propose a Nonlinear Conjugate Gradient (NLCG) optimizer for model-based T2/T1…

MRI ReconstructionQuantitative MRIZero-Shot Learning