Search Results for author: Sidharth Kumar

Found 7 papers, 3 papers with code

Solving Inverse Problems with Score-Based Generative Priors learned from Noisy Data

no code implementations2 May 2023 Asad Aali, Marius Arvinte, Sidharth Kumar, Jonathan I. Tamir

We present SURE-Score: an approach for learning score-based generative models using training samples corrupted by additive Gaussian noise.


Accelerated Motion Correction with Deep Generative Diffusion Models

1 code implementation1 Nov 2022 Brett Levac, Sidharth Kumar, Ajil Jalal, Jonathan I. Tamir

In this work we propose a framework for jointly reconstructing highly sub-sampled MRI data while estimating patient motion using diffusion based generative models.

Image Reconstruction

FSE Compensated Motion Correction for MRI Using Data Driven Methods

no code implementations1 Jul 2022 Brett Levac, Sidharth Kumar, Sofia Kardonik, Jonathan I. Tamir

Magnetic Resonance Imaging (MRI) is a widely used medical imaging modality boasting great soft tissue contrast without ionizing radiation, but unfortunately suffers from long acquisition times.

Few-Max: Few-Shot Domain Adaptation for Unsupervised Contrastive Representation Learning

1 code implementation21 Jun 2022 Ali Lotfi Rezaabad, Sidharth Kumar, Sriram Vishwanath, Jonathan I. Tamir

Pretraining on a large source data set and fine-tuning on the target samples is prone to overfitting in the few-shot regime, where only a small number of target samples are available.

Contrastive Learning Domain Adaptation +3

An untrained deep learning method for reconstructing dynamic magnetic resonance images from accelerated model-based data

no code implementations3 May 2022 Kalina P. Slavkova, Julie C. DiCarlo, Viraj Wadhwa, Chengyue Wu, John Virostko, Sidharth Kumar, Thomas E. Yankeelov, Jonathan I. Tamir

We conclude that the use of an untrained neural network together with a physics-based regularization loss shows promise as a measure for determining the optimal stopping point in training without relying on fully-sampled ground truth data.


End-to-End Radio Fingerprinting with Neural Networks

no code implementations11 Oct 2020 Ryan M. Dreifuerst, Andrew Graff, Sidharth Kumar, Clive Unger, Dylan Bray

This paper presents a novel method for classifying radio frequency (RF) devices from their transmission signals.

General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.