3 papers
cs.LG2025
Score Combining for Contrastive OOD Detection
Edward T. Reehorst, Philip Schniter
In out-of-distribution (OOD) detection, one is asked to classify whether a test sample comes from a known inlier distribution or not. We focus on the case where the inlier distribu…
cs.CV2024
Fast and Robust Phase Retrieval via Deep Expectation-Consistent Approximation
Saurav K. Shastri, Philip Schniter
Accurately recovering images from phaseless measurements is a challenging and long-standing problem. In this work, we present "deepECpr," which combines expectation-consistent (EC)…
eess.IV2024
MRI Recovery with Self-Calibrated Denoisers without Fully-Sampled Data
Muhammad Shafique, Sizhuo Liu, Philip Schniter +1
Objective: Acquiring fully sampled training data is challenging for many MRI applications. We present a self-supervised image reconstruction method, termed ReSiDe, capable of recov…