# Variance-Aware Weight Initialization for Point Convolutional Neural Networks

arXiv: https://arxiv.org/abs/2112.03777 · HTML: https://mlsanity.com/paper/2112.03777/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 23 references that are in the map.
- First posted on arXiv 7 Dec 2021.

## Builds on (most cited first, 21 of 21)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [PointConv: Deep Convolutional Networks on 3D Point Clouds](https://mlsanity.com/paper/1811.07246/) (2018)
- [Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data](https://mlsanity.com/paper/1908.04616/) (2019)
- [Point Convolutional Neural Networks by Extension Operators](https://mlsanity.com/paper/1803.10091/) (2018)
- [Pointwise Convolutional Neural Networks](https://mlsanity.com/paper/1712.05245/) (2017)
- [Mix3D: Out-of-Context Data Augmentation for 3D Scenes](https://mlsanity.com/paper/2110.02210/) (2021)
- [All you need is a good init](https://mlsanity.com/paper/1511.06422/) (2015)
- [Interpolated Convolutional Networks for 3D Point Cloud Understanding](https://mlsanity.com/paper/1908.04512/) (2019)
- [Monte Carlo Convolution for Learning on Non-Uniformly Sampled Point Clouds](https://mlsanity.com/paper/1806.01759/) (2018)
- [ConvPoint: Continuous Convolutions for Point Cloud Processing](https://mlsanity.com/paper/1904.02375/) (2019)
- [Octree guided CNN with Spherical Kernels for 3D Point Clouds](https://mlsanity.com/paper/1903.00343/) (2019)
- [Data-dependent Initializations of Convolutional Neural Networks](https://mlsanity.com/paper/1511.06856/) (2015)
- [Flex-Convolution (Million-Scale Point-Cloud Learning Beyond Grid-Worlds)](https://mlsanity.com/paper/1803.07289/) (2018)

## Abstract (arXiv)

Appropriate weight initialization has been of key importance to successfully train neural networks. Recently, batch normalization has diminished the role of weight initialization by simply normalizing each layer based on batch statistics. Unfortunately, batch normalization has several drawbacks when applied to small batch sizes, as they are required to cope with memory limitations when learning on point clouds. While well-founded weight initialization strategies can render batch normalization unnecessary and thus avoid these drawbacks, no such approaches have been proposed for point convolutional networks. To fill this gap, we propose a framework to unify the multitude of continuous convolutions. This enables our main contribution, variance-aware weight initialization. We show that this initialization can avoid batch normalization while achieving similar and, in some cases, better performance.