Vector Neurons: A General Framework for SO(3)-Equivariant Networks

04/25/2021
by   Congyue Deng, et al.
11

Invariance and equivariance to the rotation group have been widely discussed in the 3D deep learning community for pointclouds. Yet most proposed methods either use complex mathematical tools that may limit their accessibility, or are tied to specific input data types and network architectures. In this paper, we introduce a general framework built on top of what we call Vector Neuron representations for creating SO(3)-equivariant neural networks for pointcloud processing. Extending neurons from 1D scalars to 3D vectors, our vector neurons enable a simple mapping of SO(3) actions to latent spaces thereby providing a framework for building equivariance in common neural operations – including linear layers, non-linearities, pooling, and normalizations. Due to their simplicity, vector neurons are versatile and, as we demonstrate, can be incorporated into diverse network architecture backbones, allowing them to process geometry inputs in arbitrary poses. Despite its simplicity, our method performs comparably well in accuracy and generalization with other more complex and specialized state-of-the-art methods on classification and segmentation tasks. We also show for the first time a rotation equivariant reconstruction network.

READ FULL TEXT

page 4

page 8

research
05/19/2022

VNT-Net: Rotational Invariant Vector Neuron Transformers

Learning 3D point sets with rotational invariance is an important and ch...
research
06/08/2022

VN-Transformer: Rotation-Equivariant Attention for Vector Neurons

Rotation equivariance is a desirable property in many practical applicat...
research
05/20/2017

Forward Thinking: Building Deep Random Forests

The success of deep neural networks has inspired many to wonder whether ...
research
06/23/2020

NeuralScale: Efficient Scaling of Neurons for Resource-Constrained Deep Neural Networks

Deciding the amount of neurons during the design of a deep neural networ...
research
10/04/2021

Max and Coincidence Neurons in Neural Networks

Network design has been a central topic in machine learning. Large amoun...
research
07/18/2022

Residual and Attentional Architectures for Vector-Symbols

Vector-symbolic architectures (VSAs) provide methods for computing which...
research
09/05/2023

Information Processing by Neuron Populations in the Central Nervous System: Mathematical Structure of Data and Operations

In the intricate architecture of the mammalian central nervous system, n...

Please sign up or login with your details

Forgot password? Click here to reset