UnU-Net: Distance-Aware Uncertainty Quantification for Semantic Segmentation
الملخص
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.
الكلمات المفتاحية
غير متوفر
التخصصات
رسائل وأطاريح مشابهة
- Quantifying Uncertainty in Deep Learning-based medical image segmentation Benjamin Lambert · 2023
- Learning with imperfect datasets in medical image segmentation Yuhang Ding · University of Technology Sydney · 2024
- Improving LULC Map Production via Semantic Segmentation and Unsupervised Domain Adaptation Rostyslav-Mykola Tsenov · 2021
- Interpretability of a Deep Learning Model for Semantic Segmentation : Example of Remote Sensing Application Adrianna Janik · KTH Royal Institute of Technology · 2019
- Computer Vision for Aircraft Fuselage Defect Detection: A YOLO11-Based Approach Pedro Afonso Bruno Arroteia · 2025
- Computer Vision for Automated Robotic Device Disassembly: Object Detection, Pose Estimation, and Action Prediction Ruiz, Sebastian · Georg-August-Universität Göttingen · 2024
