论文标题
评估点云的3D语义分割的不确定性估计方法
Evaluating Uncertainty Estimation Methods on 3D Semantic Segmentation of Point Clouds
论文作者
论文摘要
深度学习模型广泛用于各种安全关键应用。因此，这些模型以及准确的需要非常可靠。实现这一目标的一种方法是量化不确定性。已对UQ的贝叶斯方法进行了广泛的研究，用于用于图像上的深度学习模型，但对3D模式（例如通常用于机器人和自主系统的点云）进行了探索。在这项工作中，我们评估了三种不确定性量化方法，即对DarkNet21Seg 3D语义分割模型的MC-Dropout和MC-DropConnect，并全面分析了各种参数的影响，例如模型数量或远期通行证中的模型数量，以及对任务性能和不确定性的质量和不确定性估算质量的影响。我们发现，深层合奏在性能和不确定性指标中的其他方法都优于其他方法。在MIOU方面，Deep合奏的幅度优于2.4％，而准确性为1.3％，同时为决策提供了可靠的不确定性。
Deep learning models are extensively used in various safety critical applications. Hence these models along with being accurate need to be highly reliable. One way of achieving this is by quantifying uncertainty. Bayesian methods for UQ have been extensively studied for Deep Learning models applied on images but have been less explored for 3D modalities such as point clouds often used for Robots and Autonomous Systems. In this work, we evaluate three uncertainty quantification methods namely Deep Ensembles, MC-Dropout and MC-DropConnect on the DarkNet21Seg 3D semantic segmentation model and comprehensively analyze the impact of various parameters such as number of models in ensembles or forward passes, and drop probability values, on task performance and uncertainty estimate quality. We find that Deep Ensembles outperforms other methods in both performance and uncertainty metrics. Deep ensembles outperform other methods by a margin of 2.4% in terms of mIOU, 1.3% in terms of accuracy, while providing reliable uncertainty for decision making.
