A subgroup-based downsampling layer with an equivariant anti-aliasing projection for finite groups, shown to cut parameters and modestly improve equivariance and rotated-input accuracy in small G-CNN experiments.
Truly shift-invariant convolutional neural networks
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
-
Group Downsampling with Equivariant Anti-aliasing
A subgroup-based downsampling layer with an equivariant anti-aliasing projection for finite groups, shown to cut parameters and modestly improve equivariance and rotated-input accuracy in small G-CNN experiments.