An Empirical Review of Uncertainty Estimation for Quality Control in CAD Model Segmentation

Vidanes, Gerico, Toal, David, Keane, Andy, Zhang, Xu ORCID: https://orcid.org/0000-0002-6918-1861, Nunez, Marco and Gregory, Jon (2025) An Empirical Review of Uncertainty Estimation for Quality Control in CAD Model Segmentation. In: Engineering Applications of Neural Networks. EANN 2025, 26 – 29 June, 2025, Limassol - Cyprus.

Text (A paper has been accepted and published by AIAI / EANN 2025 Conference) GV_uncertaintypaper_250325.pdf - Accepted Version Restricted to Repository staff only until 22 June 2026. Available under License All Rights Reserved. Download (1MB) | Request a copy

Abstract / Summary

Deep neural networks are able to achieve high accuracy in semantic segmentation of geometries used in computational engineering. Being able to recognise abstract and sometimes hard to describe geometric features has applications for automated simulation, model simplification, structural failure analysis, meshing, and additive manufacturing. However, for these systems to be integrated into engineering workflows, they must provide some measures of predictive uncertainty such that engineers can reason about and trust their outputs. This work presents an empirical study of practical uncertainty estimation techniques that can be used with pre-trained neural networks for the task of boundary representation model segmentation. A point-based graph neural network is used as a base. Monte-Carlo Dropout (MCD), Deep Ensembles, test time input augmentation, and post-processing calibration are evaluated for segmentation quality control. The Deep Ensemble technique is found to be top performing and the error of a human-in-the-loop system across a dataset can be reduced from 3.8% to 0.7% for MFCAD++ and from 16% to 11% for Fusion360 Gallery when 10% of the most uncertain predictions are flagged for manual correction. Models trained on only 5% of the MFCAD++ dataset were also tested, with the uncertainty estimation technique reducing the error from 9.4% to 4.3% with 10% of predictions flagged. Additionally, a point-based input augmentation is presented; which, when combined with MCD, is competitive with the Deep Ensemble while having lower computational requirements.

Item Type:	Conference or Workshop Item (Paper)
Subjects:	Computing & Data Science
Department:	Games Academy
Depositing User:	Daniel Zhang
Date Deposited:	07 Jul 2025 14:55
Last Modified:	07 Jul 2025 14:55
URI:	https://repository.falmouth.ac.uk/id/eprint/6105

View Record (staff only)