Unsupervised symmetry discovery via shallow group-convolutional networks recovers latent domains from linear measurements of random fields by learning symmetry actions under stationarity and locality constraints.
Fast, expressive se(n) equivariant networks through weight-sharing in position-orientation space, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Blind Recovery of Latent Domains via Unsupervised Symmetry Discovery
Unsupervised symmetry discovery via shallow group-convolutional networks recovers latent domains from linear measurements of random fields by learning symmetry actions under stationarity and locality constraints.