Implicit Convolutional Kernels for Steerable CNNs

2022-12-12 · NeurIPS 2023 11 · Maksim Zhdanov, Nico Hoffmann, Gabriele Cesa

Steerable convolutional neural networks (CNNs) provide a general framework for building neural networks equivariant to translations and transformations of an origin-preserving group $G$, such as reflections and rotations. They rely on standard convolutions with $G$-steerable kernels obtained by analytically solving the group-specific equivariance constraint imposed onto the kernel space. As the solution is tailored to a particular group $G$, implementing a kernel basis does not generalize to other symmetry transformations, complicating the development of general group equivariant models. We propose using implicit neural representation via multi-layer perceptrons (MLPs) to parameterize $G$-steerable kernels. The resulting framework offers a simple and flexible way to implement Steerable CNNs and generalizes to any group $G$ for which a $G$-equivariant MLP can be built. We prove the effectiveness of our method on multiple tasks, including N-body simulations, point cloud classification and molecular property prediction.

📄 PDF Abstract BibTeX arXiv:2212.06096

Code (1)

maxxxzdn/implicit-steerable-kernels 공식 구현 pytorch

Tasks

Molecular Property Prediction Point Cloud ClassificationProperty Prediction

Clifford-Steerable Convolutional Neural Networks

2024-02-22 · Maksim Zhdanov, David Ruhe, Maurice Weiler, Ana Lucic 외

We present Clifford-Steerable Convolutional Neural Networks (CS-CNNs), a novel class of $\mathrm{E}(p, q)$-equivariant CNNs. CS-CNNs process multivector fields on pseudo-Euclidean spaces $\mathbb{R}^{p,q}$. They cover, f…

A Wigner-Eckart Theorem for Group Equivariant Convolution Kernels

2020-10-21 · ICLR 2021 1 · Leon Lang, Maurice Weiler

Group equivariant convolutional networks (GCNNs) endow classical convolutional networks with additional symmetry priors, which can lead to a considerably improved performance. Recent advances in the theoretical descripti…

Conditional Clifford-Steerable CNNs for PDE Modeling

2025-10-15 · Bálint László Szarvas, Maksim Zhdanov arxiv

We introduce Conditional Clifford-Steerable CNNs (C-CSCNNs), a unified framework that incorporates equivariance to arbitrary pseudo-Euclidean groups and significantly improves the expressivity of standard CSCNNs. We show…

Leveraging SO(3)-steerable convolutions for pose-robust semantic segmentation in 3D medical data

2023-03-01 · Ivan Diaz, Mario Geiger, Richard Iain McKinley

Convolutional neural networks (CNNs) allow for parameter sharing and translational equivariance by using convolutional kernels in their linear layers. By restricting these kernels to be SO(3)-steerable, CNNs can further …

Data Augmentation Medical Image Analysis Segmentation Semantic Segmentation

Bayesian 3D Steerable CNNs: Enabling Equivariance and Uncertainty Quantification Simultaneously

2026-06-13 · Abhishek Keripale, Ponkrshnan Thiagarajan, Susanta Ghosh arxiv

Steerable convolutional neural networks (Steerable-CNNs) guarantee SE(3)-equivariance by parameterizing kernels as linear combinations of steerable basis functions, but their deterministic nature precludes uncertainty qu…