We Know Where We Don’t Know: 3D Bayesian CNNs for Credible Geometric Uncertainty
Tyler LaBonte 1122 Carianne Martinez 11 Scott A. Roberts 11
Abstract
Deep learning has been successfully applied to the segmentation of 3D Computed Tomography (CT) scans. Establishing the credibility of these segmentations requires uncertainty quantification (UQ) to identify untrustworthy predictions. Recent UQ architectures include Monte Carlo dropout networks (MCDNs), which approximate deep Gaussian processes, and Bayesian neural networks (BNNs), which learn the distribution of the weight space. BNNs are advantageous over MCDNs for UQ but are thought to be computationally infeasible in high dimension, and neither architecture has produced interpretable geometric uncertainty maps. We propose a novel 3D Bayesian convolutional neural network (BCNN), the first deep learning method which generates statistically credible geometric uncertainty maps and scales for application to 3D data. We present experimental results on CT scans of graphite electrodes and laser-welded metals and show that our BCNN outperforms an MCDN in recent uncertainty metrics. The geometric uncertainty maps generated by our BCNN capture distributions of sigmoid values that are interpretable as confidence intervals, critical for applications that rely on deep learning for high-conseq
中文速览
用深度学习自动分割三维CT扫描图像时，如何量化模型预测的不确定性、让结果真正可信，一直是工业质检和安全认证领域的难题。研究团队提出了一种三维贝叶斯卷积神经网络（Bayesian CNN, BCNN），通过在网络解码器的权重上学习概率分布，而非给出单一的点估计，从而在权重空间而非输出空间度量不确定性，使生成的几何不确定性图可以直接解读为分割结果的置信区间。在石墨电极和激光焊接金属的CT扫描数据集上，该BCNN在主流不确定性评估指标上均优于常用的蒙特卡洛随机失活网络（Monte Carlo Dropout Network, MCDN），并首次生成了具有统计可信度、视觉上连续可解释的几何不确定性热力图。这一成果打破了"贝叶斯神经网络无法扩展到三维高维场景"的固有认知，为航空航天、汽车制造等高风险决策场景中依赖深度学习进行材料分析提供了可量化的安全保障。
原文 arXiv:1910.10793;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1910.10793v2