equivariant neural networks
Equivariant neural networks are designed to maintain certain symmetries and transformations across inputs and outputs, improving performance in tasks where such properties are important, such as in 3D data processing.
- A Practical Guide for Incorporating Symmetry in Diffusion Policy
- A Tale of Two Symmetries: Exploring the Loss Landscape of Equivariant Models
- Bridging Equivariant GNNs and Spherical CNNs for Structured Physical Domains
- Learning (Approximately) Equivariant Networks via Constrained Optimization
- Learning (Approximately) Equivariant Networks via Constrained Optimization
- On Universality Classes of Equivariant Networks
- On the VC dimension of deep group convolutional neural networks