Journal
2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021)
Volume -, Issue -, Pages 14025-14031Publisher
IEEE
DOI: 10.1109/ICRA48506.2021.9560972
Keywords
-
Categories
Funding
- Fundamental Research Funds for the Central Universities [2020XD-A04-1]
- National Natural Science Foundation of China [61673192]
Ask authors/readers for more resources
This paper proposes a method called NSA-MC dropout for efficient uncertainty estimation in point cloud semantic segmentation, which achieves uncertainty estimation through one-time inference and outperforms traditional MC dropout in terms of efficiency and impact on semantic inference.
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 depending 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
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available