12 papers
A Principled Self-Referenced Early Stopping Approach for Deep Image Prior
Chaoyan Huang, Cheng-Han Huang, Ismail R. Alkhouri +1
Recently, Deep Image Prior (DIP) has demonstrated strong capabilities for solving inverse imaging problems (IIPs) by optimizing a randomly initialized convolutional neural network…
MCLR: Improving Conditional Modeling via Inter-Class Likelihood-Ratio Maximization and Unifying Classifier-Free Guidance with Alignment Objectives
Xiang Li, Yixuan Jia, Xiao Li +3
Diffusion models achieve strong performance in generative modeling, but their success often relies heavily on classifier-free guidance (CFG), an inference-time heuristic that modif…
A Scalable Lift-and-Project Differentiable Approach For the Maximum Cut Problem
Ismail Alkhouri, Mian Wu, Cunxi Yu +3
We propose a scalable framework for solving the Maximum Cut (MaxCut) problem in large graphs using projected gradient ascent on quadratic objectives. Our approach is differentiable…
Understanding Untrained Deep Models for Inverse Problems: Algorithms and Theory
Ismail Alkhouri, Evan Bell, Avrajit Ghosh +3
In recent years, deep learning methods have been extensively developed for inverse imaging problems (IIPs), encompassing supervised, self-supervised, and generative approaches. Mos…
Robust Physics-based Deep MRI Reconstruction Via Diffusion Purification
Ismail Alkhouri, Shijun Liang, Rongrong Wang +2
Deep learning (DL) techniques have been extensively employed in magnetic resonance imaging (MRI) reconstruction, delivering notable performance enhancements over traditional non-DL…
NERD: Network-Regularized Diffusion Sampling For 3D Computed Tomography
Shijun Liang, Ismail Alkhouri, Qing Qu +2
Numerous diffusion model (DM)-based methods have been proposed for solving inverse imaging problems. Among these, a recent line of work has demonstrated strong performance by formu…