# Neighborhood Spatial Aggregation MC Dropout for Efficient Uncertainty-aware Semantic Segmentation in Point Clouds

arXiv: https://arxiv.org/abs/2201.07676 · HTML: https://mlsanity.com/paper/2201.07676/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 65 references that are in the map.
- First posted on arXiv 5 Dec 2021.

## Builds on (most cited first, 29 of 29)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [PCT: Point cloud transformer](https://mlsanity.com/paper/2012.09688/) (2020)
- [RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds](https://mlsanity.com/paper/1911.11236/) (2019)
- [Deep Learning for 3D Point Clouds: A Survey](https://mlsanity.com/paper/1912.12033/) (2019)
- [Weight Uncertainty in Neural Networks](https://mlsanity.com/paper/1505.05424/) (2015)
- [Variational Dropout and the Local Reparameterization Trick](https://mlsanity.com/paper/1506.02557/) (2015)
- [Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation](https://mlsanity.com/paper/1907.07034/) (2019)
- [Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding](https://mlsanity.com/paper/1511.02680/) (2015)
- [Probabilistic End-to-end Noise Correction for Learning with Noisy Labels](https://mlsanity.com/paper/1903.07788/) (2019)
- [SEGCloud: Semantic Segmentation of 3D Point Clouds](https://mlsanity.com/paper/1710.07563/) (2017)
- [Constrained Bayesian Optimization with Noisy Experiments](https://mlsanity.com/paper/1706.07094/) (2017)
- [Uncertainty-guided Continual Learning with Bayesian Neural Networks](https://mlsanity.com/paper/1906.02425/) (2019)
- [Uncertainty-aware multi-view co-training for semi-supervised medical image segmentation and domain adaptation](https://mlsanity.com/paper/2006.16806/) (2020)
- [Sampling-free Epistemic Uncertainty Estimation Using Approximated Variance Propagation](https://mlsanity.com/paper/1908.00598/) (2019)
- [Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusion](https://mlsanity.com/paper/2103.07074/) (2021)
- [Paris-Lille-3D: a large and high-quality ground truth urban point cloud dataset for automatic segmentation and classification](https://mlsanity.com/paper/1712.00032/) (2017)
- [Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds](https://mlsanity.com/paper/1909.09287/) (2019)
- [Uncertainty Inspired RGB-D Saliency Detection](https://mlsanity.com/paper/2009.03075/) (2020)
- [Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling](https://mlsanity.com/paper/2107.02389/) (2021)
- [Efficient Uncertainty Estimation for Semantic Segmentation in Videos](https://mlsanity.com/paper/1807.11037/) (2018)
- [Double-Uncertainty Weighted Method for Semi-supervised Learning](https://mlsanity.com/paper/2010.09298/) (2020)
- [Learning with Noisy Labels for Robust Point Cloud Segmentation](https://mlsanity.com/paper/2107.14230/) (2021)
- [Leveraging Heteroscedastic Aleatoric Uncertainties for Robust Real-Time LiDAR 3D Object Detection](https://mlsanity.com/paper/1809.05590/) (2018)
- [Scalable Joint Models for Reliable Uncertainty-Aware Event Prediction](https://mlsanity.com/paper/1708.04757/) (2017)

## Built on by (most cited first, 1 of 1)

- [A Review of Bayesian Uncertainty Quantification in Deep Probabilistic Image Segmentation](https://mlsanity.com/paper/2411.16370/) (2024)

## Abstract (arXiv)

Uncertainty-aware semantic segmentation of the point clouds includes the predictive uncertainty estimation and the uncertainty-guided model optimization. One key challenge in the task is the efficiency of point-wise predictive distribution establishment. The widely-used MC dropout establishes the distribution by computing the standard deviation of samples using multiple stochastic forward propagations, which is time-consuming for tasks based on point clouds containing massive points. Hence, a framework embedded with NSA-MC dropout, a variant of MC dropout, is proposed to establish distributions in just one forward pass. Specifically, the NSA-MC dropout samples the model many times through a space-dependent way, outputting point-wise distribution by aggregating stochastic inference results of neighbors. Based on this, aleatoric and predictive uncertainties acquire from the predictive distribution. The aleatoric uncertainty is integrated into the loss function to penalize noisy points, avoiding the over-fitting of the model to some degree. Besides, the predictive uncertainty quantifies the confidence degree of predictions. Experimental results show that our framework obtains better segmentation results of real-world point clouds and efficiently quantifies the credibility of results. Our NSA-MC dropout is several times faster than MC dropout, and the inference time does not establish a coupling relation with the sampling times. The code will be available if the paper is accepted.