Feature-space sampling in GCNNs preserves 3D classification accuracy with coarse discretization, enabling precomputation and faster training of equivariant models.
3D steerable CNNs: Learning rotationally equivariant features in volumetric data.Advances in Neural information processing systems, 31, 2018a
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
Adaptive canonicalization selects input canonical forms by maximizing network predictive confidence to yield continuous symmetry-preserving models with universal approximation for equivariant geometric networks.
Introduces Hodge Spectral Duality, a hybrid neural architecture that applies Hodge orthogonality and operator splitting to isolate unlearnable topological degrees of freedom from learnable geometric dynamics in solution operators on geometric meshes.
A JAX-implemented flow-based equivariant model for multi-embodiment grasping that deduces kinematics from geometry to support variable-DoF grippers with a new dataset of 25k scenes and 20M grasps.
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.
-
Adaptive Canonicalization with Application to Invariant Anisotropic Geometric Networks
Adaptive canonicalization selects input canonical forms by maximizing network predictive confidence to yield continuous symmetry-preserving models with universal approximation for equivariant geometric networks.
-
Topology-Preserving Neural Operator Learning via Hodge Decomposition
Introduces Hodge Spectral Duality, a hybrid neural architecture that applies Hodge orthogonality and operator splitting to isolate unlearnable topological degrees of freedom from learnable geometric dynamics in solution operators on geometric meshes.
-
Towards a Multi-Embodied Grasping Agent
A JAX-implemented flow-based equivariant model for multi-embodiment grasping that deduces kinematics from geometry to support variable-DoF grippers with a new dataset of 25k scenes and 20M grasps.