Rotation Equivariant Operators for Machine Learning on Scalar and Vector Fields
We develop theory and software for rotation equivariant operators on scalar and vector fields, with diverse applications in simulation, optimization and machine learning. Rotation equivariance (covariance) means all fields in the system rotate together, implying spatially invariant dynamics that preserve symmetry. Extending the convolution theorems of linear time invariant systems, we theorize that linear equivariant operators are characterized by tensor field convolutions using an appropriate product between the input field and a radially symmetric kernel field. Most Green's functions and differential operators are in fact equivariant operators, which can also fit unknown symmetry preserving dynamics by parameterizing the radial function. We implement the Julia package EquivariantOperators.jl for fully differentiable finite difference equivariant operators on scalar, vector and higher order tensor fields in 2d/3d. It can run forwards for simulation or image processing, or be back propagated for computer vision, inverse problems and optimal control. Code at https://aced-differentiate.github.io/EquivariantOperators.jl/
Code (1)
Tasks
BIG-bench Machine LearningTranslationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
When Do Geometric Algebra Layers Beat Scalarization? A Controlled Study on SO(3)-Equivariant Vector Laws
Compact networks built from Clifford algebra Cl(3,0) primitives are exactly SO(3)-equivariant and learn synthetic 3D vector laws from few samples. We ask whether the geometric algebra structure itself contributes anythin…
Scalars are universal: Equivariant machine learning, structured like classical physics
There has been enormous progress in the last few years in designing neural networks that respect the fundamental symmetries and coordinate freedoms of physical law. Some of these frameworks make use of irreducible repres…
BIG-bench Machine LearningTranslationVN-Transformer: Rotation-Equivariant Attention for Vector Neurons
Rotation equivariance is a desirable property in many practical applications such as motion forecasting and 3D perception, where it can offer benefits like sample efficiency, better generalization, and robustness to inpu…
3D Shape ClassificationMotion ForecastingSO(3)-Equivariant Neural Networks for Learning Vector Fields on Spheres
Analyzing vector fields on the sphere, such as wind speed and direction on Earth, is a difficult task. Models should respect both the rotational symmetries of the sphere and the inherent symmetries of the vector fields. …
On Invariance, Equivariance, Correlation and Convolution of Spherical Harmonic Representations for Scalar and Vectorial Data
The mathematical representations of data in the Spherical Harmonic (SH) domain has recently regained increasing interest in the machine learning community. This technical report gives an in-depth introduction to the theo…