Research map / Probabilistic and scientific modeling / Molecules and proteins
Projective Equivariant Networks via Second-order Fundamental Differential Invariants
Yikang Li, Yeqing Qiu, Yuxuan Chen, Lingshen He, Lexiang Hu, Zhouchen Lin
Read the paperCheck your idea against 137,217 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 projective-equivariant networks built from second-order fundamental differential invariants, targeting the projective group that group and steerable convolutions handle poorly.
Problem
Equivariant networks for complex transformation groups, especially the projective group important in vision, where group convolutions and steerable convolutions have significant limitations.
Approach
Constructs equivariant networks for the projective group by using second-order fundamental differential invariants as the building blocks, rather than group or steerable convolutions.
Experimental setup
Builds on: group convolution steerable convolution
Closest papers by meaning
- Affine Equivariant Networks Based on Differential Invariants (CVPR 2024 · similarity 0.90)
- Towards Diffeomorphism-Equivariant Neural Networks via Canonicalization (ICML 2026 · similarity 0.89)
- Probing Equivariance and Symmetry Breaking in Convolutional Networks (NeurIPS 2025 · similarity 0.88)
- Lie Group Decompositions for Equivariant Neural Networks (ICLR 2024 · similarity 0.88)
- Neural Isometries: Taming Transformations for Equivariant ML (NeurIPS 2024 · similarity 0.87)
- A Characterization Theorem for Equivariant Networks with Point-wise Activations (ICLR 2024 · similarity 0.87)
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.
