paper-conference

Generalized Reduction to the Isotropy for Flexible Equivariant Neural Fields
Many geometric learning problems require invariants on heterogeneous product spaces, i.e., products of distinct spaces carrying …
Alejandro Garcı́a-Castellanos, Gijs Bellaard, Remco Duits, Daniel Pelt, Erik J Bekkers
PDF Cite
Generalized Reduction to the Isotropy for Flexible Equivariant Neural Fields
Learning symmetries via weight-sharing with doubly stochastic tensors
Traditional group equivariant methods presuppose known groups, an assumption that can be unrealistic for real-world datasets and …
Putri A. van der Linden, Alejandro García-Castellanos, Sharvaree P. Vadgama, Thijs P. Kuipers, Erik J. Bekkers
PDF Cite
Learning symmetries via weight-sharing with doubly stochastic tensors
Relative Representations: Topological and Geometric Perspectives
Relative representations are an established approach to zero-shot model stitching, consisting of a non-trainable transformation of the …
Alejandro Garcı́a-Castellanos, Giovanni Luca Marchetti, Danica Kragic, Martina Scolamiero
PDF Cite Code Poster
Relative Representations: Topological and Geometric Perspectives