Adaptive Canonicalization
1 mentions across 1 person
All mentions
“In this paper, we address this by introducing adaptive canonicalization, a general framework in which the canonicalization depends both on the input and the network. Specifically, we present the adaptive canonicalization based on prior maximization, where the standard form of the input is chosen to maximize the predictive confidence of the network. We prove that this construction yields continuous and symmetry-respecting models that admit u”
Adaptive Canonicalization for Continuous Equivariant Learning ↗