Combining BCOP and RKO kernels with a channel-sizing rule yields orthogonal convolutions with native stride, transpose, group, and dilation support.
The model reached its maximum generalization for this margin
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
An Adaptive Orthogonal Convolution Scheme for Efficient and Flexible CNN Architectures
Combining BCOP and RKO kernels with a channel-sizing rule yields orthogonal convolutions with native stride, transpose, group, and dilation support.