Back to search

Virginia Tech

UnU-Net: Distance-Aware Uncertainty Quantification for Semantic Segmentation

Abstract

dc:description.abstract

Automated mechanical inspections increasingly rely on deep learning models for semantic segmentations of faults. However, standard deterministic models, such as U-Net, are prone to overconfident misclassifications on Out of Distribution (OOD) Data, posing severe risk of silent failures from a confident misclassification. Although methods like Deep Ensembles and Monte Carlo (MC) Dropout provide benchmarks for uncertainty quantification, their use during inference requires multiple forward passes increasing the computational overhead linearly making real time applications challenging. To address this gap, we introduce UnU-Net, a distance aware probabilistic architecture that incorporates a Spectral Normalized Neural Gaussian Process (SNGP) with the final pixel-wise prediction. By replacing conventional normalization techniques with Group Normalization and constraining the weights via Spectral Normalization, UnU-Net prevents feature collapse ensuring a preserved latent space distance. Evaluated on the Carvana and DeepCrack segmentation datasets, UnU-Net extracts precise segmentation masks and quantifies epistemic uncertainty flagging anomalies in a single forward pass. This architecture maintains the accuracy of the standard U-Net and outperforms conventional UQ methods while only requiring a single forward pass.

Degree

thesis:*
Name thesis:degree_name
Master of Science
Level thesis:degree_level
masters
Discipline thesis:degree_discipline
Mechanical Engineering
Department dc:contributor.department
Mechanical Engineering
Grantor dc:publisher
Virginia Tech
Year dc:date.issued
2026

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Linville, Andrew William
Chair dc:contributor.committeechair
  • Chen, Jie
Committee members dc:contributor.committeemember
  • Nowinski, Matthew Clarke
  • Wicks, Alfred L.

Subjects

dc:subject × 4

Rights

dc:rights
Statement dc:rights
  • In Copyright
Language dc:language.iso
en

Identifiers

dc:identifier.*
Dc Identifier Other
vt_gsexam:46815

Chain of custody

source
Harvested from
Virginia Tech
Base URL
vtechworks.lib.vt.edu/oai/request
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
citation

Linville, Andrew William. UnU-Net: Distance-Aware Uncertainty Quantification for Semantic Segmentation. masters thesis, Virginia Tech, 2026. https://hdl.handle.net/10919/143061