Neighborhood Spatial Aggregation based Efficient Uncertainty Estimation for Point Cloud Semantic Segmentation

Uncertainty estimation for point cloud semantic segmentation is to quantify the confidence degree for the predicted label of points, which is essential for decision-making tasks. This paper proposes a neighborhood spatial aggregation based method, NSA-MC dropout, to achieve efficient uncertainty estimation for point cloud semantic segmentation. Unlike the traditional uncertainty estimation method MC dropout de-pending on repeated inferences, our NSA-MC dropout achieves uncertainty estimation through one-time inference. Specifically, a space-dependent method is designed to sample the model many times by performing stochastic forward pass through the model just once, and it approximates the repeated inferences based sampling process in MC dropout. Besides, a neighborhood spatial aggregation module, called NSA, aggregates neighborhood probabilistic outputs for each point and works with space-dependent sampling to establish output distribution. Finally, we propose an uncertainty-aware framework NSA-MC dropout to capture the uncertainty of prediction results efficiently. Experimental results show that our method obtains comparable performance with MC dropout. More significantly, our NSA-MC dropout has little influence on the efficiency of semantic inference. It is much faster than MC dropout, and the inference time does not establish a coupling relation with the sampling times. Our code is available at https://github.com/chaoqi7/Uncertainty_Estimation_PCSS

I. INTRODUCTION

Uncertainty estimation for point cloud semantic segmentation (PCSS) helps us to know how much we can trust the predicted label of points. It is essential for decision-making applications, such as robotic grasping, path planning, and self-driving. However, the uncertainty estimation relies on an establishment of output distribution, which needs a great amount of computation. It poses a considerable challenge to uncertainty estimation for semantic segmentation tasks based on the large-scale point cloud, especially for those with high-efficiency requirements. Thus, we explore a method to achieve efficient uncertainty estimation of PCSS.