Research map / Architectures and efficiency / CNN design
Affine Steerable Equivariant Layer for Canonicalization of Neural Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes the steerable EquivarLayer, a generalization of InvarLayer that gives affine-equivariant layers for arbitrary input and output group representations.
Problem
Achieving affine equivariance in neural networks, especially for general group representations, has been a long-standing challenge.
Approach
Generalizes InvarLayer (Li et al., 2024) from invariant to equivariant outputs by building a steerable layer that supports affine equivariance with arbitrary input and output representations.
Experimental setup
Builds on: InvarLayer
Closest papers by meaning
- Affine Equivariant Networks Based on Differential Invariants (CVPR 2024 · similarity 0.92)
- General E(2)-Equivariant Steerable CNNs (NeurIPS 2019 · similarity 0.91)
- A Probabilistic Approach to Learning the Degree of Equivariance in Steerable CNNs (ICML 2024 · similarity 0.90)
- A Canonicalization Perspective on Invariant and Equivariant Learning (NeurIPS 2024 · similarity 0.90)
- A Characterization Theorem for Equivariant Networks with Point-wise Activations (ICLR 2024 · similarity 0.89)
- Lie Group Decompositions for Equivariant Neural Networks (ICLR 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.