Feature-space sampling in GCNNs preserves 3D classification accuracy with coarse discretization, enabling precomputation and faster training of equivariant models.
author Wang, C
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
A new geometric optimization method generates synchronized deployment trajectories for elastic geodesic grids by approximating node paths from inverse tracing and solving a non-smooth polyline problem to drive stable finite element simulations.
REViT introduces a discrete roto-reflection equivariant convolutional vision transformer claimed to outperform prior equivariant networks on image classification.
citing papers explorer
-
Discretizing Group-Convolutional Neural Networks for 3D Geometry in Feature Space
Feature-space sampling in GCNNs preserves 3D classification accuracy with coarse discretization, enabling precomputation and faster training of equivariant models.
-
Geometric Guidance for Globally Synchronized Deployment of Elastic Geodesic Grids
A new geometric optimization method generates synchronized deployment trajectories for elastic geodesic grids by approximating node paths from inverse tracing and solving a non-smooth polyline problem to drive stable finite element simulations.
-
REViT: Roto-reflection Equivariant Convolutional Vision Transformer
REViT introduces a discrete roto-reflection equivariant convolutional vision transformer claimed to outperform prior equivariant networks on image classification.