SEIS defines subspace-based scores to measure layer-wise equivariance and invariance in neural representations under geometric transformations.
Furthermore, modern architectures process these features via linear convolutions and element-wise non- linearities that preserve local topology
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
-
SEIS: Subspace-based Equivariance and Invariance Scores for Neural Representations
SEIS defines subspace-based scores to measure layer-wise equivariance and invariance in neural representations under geometric transformations.