The Asymmetric Convolution Block trains with three parallel branches and is exactly folded back into a single square kernel, giving small accuracy gains at zero extra inference cost.
Tensorflow-alexnet
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks
The Asymmetric Convolution Block trains with three parallel branches and is exactly folded back into a single square kernel, giving small accuracy gains at zero extra inference cost.