# Noise Injection-based Regularization for Point Cloud Processing

arXiv: https://arxiv.org/abs/2103.15027 · HTML: https://mlsanity.com/paper/2103.15027/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 25 references that are in the map.
- First posted on arXiv 28 Mar 2021.

## Builds on (most cited first, 16 of 16)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [Multi-view Convolutional Neural Networks for 3D Shape Recognition](https://mlsanity.com/paper/1505.00880/) (2015)
- [Variational Dropout and the Local Reparameterization Trick](https://mlsanity.com/paper/1506.02557/) (2015)
- [Point-Voxel CNN for Efficient 3D Deep Learning](https://mlsanity.com/paper/1907.03739/) (2019)
- [DropBlock: A regularization method for convolutional networks](https://mlsanity.com/paper/1810.12890/) (2018)
- [Volumetric and Multi-View CNNs for Object Classification on 3D Data](https://mlsanity.com/paper/1604.03265/) (2016)
- [PointMixup: Augmentation for Point Clouds](https://mlsanity.com/paper/2008.06374/) (2020)
- [Regularization Strategy for Point Cloud via Rigidly Mixed Sample](https://mlsanity.com/paper/2102.01929/) (2021)
- [Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations](https://mlsanity.com/paper/1606.01305/) (2016)
- [Dominant Set Clustering and Pooling for Multi-View 3D Object Recognition](https://mlsanity.com/paper/1906.01592/) (2019)
- [Effective and Efficient Dropout for Deep Convolutional Neural Networks](https://mlsanity.com/paper/1904.03392/) (2019)
- [3D Point Cloud Classification and Segmentation using 3D Modified Fisher Vector Representation for Convolutional Neural Networks](https://mlsanity.com/paper/1711.08241/) (2017)

## Built on by (most cited first, 3 of 3)

- [SymNoise: Advancing Language Model Fine-tuning with Symmetric Noise](https://mlsanity.com/paper/2312.01523/) (2023)
- [Relevance-driven Input Dropout: an Explanation-guided Regularization Technique](https://mlsanity.com/paper/2505.21595/) (2025)
- [Understanding and Improving Noisy Embedding Techniques in Instruction Finetuning](https://mlsanity.com/paper/2605.23171/) (2026)

## Abstract (arXiv)

Noise injection-based regularization, such as Dropout, has been widely used in image domain to improve the performance of deep neural networks (DNNs). However, efficient regularization in the point cloud domain is rarely exploited, and most of the state-of-the-art works focus on data augmentation-based regularization. In this paper, we, for the first time, perform systematic investigation on noise injection-based regularization for point cloud-domain DNNs. To be specific, we propose a series of regularization techniques, namely DropFeat, DropPoint and DropCluster, to perform noise injection on the point feature maps at the feature level, point level and cluster level, respectively. We also empirically analyze the impacts of different factors, including dropping rate, cluster size and dropping position, to obtain useful insights and general deployment guidelines, which can facilitate the adoption of our approaches across different datasets and DNN architectures. We evaluate our proposed approaches on various DNN models for different point cloud processing tasks. Experimental results show our approaches enable significant performance improvement. Notably, our DropCluster brings 1.5%, 1.3% and 0.8% higher overall accuracy for PointNet, PointNet++ and DGCNN, respectively, on ModelNet40 shape classification dataset. On ShapeNet part segmentation dataset, DropCluster brings 0.5%, 0.5% and 0.2% mean Intersection-over-union (IoU) increase for PointNet, PointNet++ and DGCNN, respectively. On S3DIS semantic segmentation dataset, DropCluster improves the mean IoU of PointNet, PointNet++ and DGCNN by 3.2%, 2.9% and 3.7%, respectively. Meanwhile, DropCluster also enables the overall accuracy increase for these three popular backbone DNNs by 2.4%, 2.2% and 1.8%, respectively.