Proves regular representation must appear in latent space of finite-group equivariant encoders and enforces it via auxiliary loss to match specialized equivariant models without added parameters.
A probabilistic approach to learning the degree of equivariance in steerable CNNs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Algebraic Priors for Approximately Equivariant Networks
Proves regular representation must appear in latent space of finite-group equivariant encoders and enforces it via auxiliary loss to match specialized equivariant models without added parameters.