Using depthwise convolution to expand channels yields networks with about 60 percent of MobileNetV2's parameters and comparable CIFAR accuracy.
Title resolution pending
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
-
PSDNet and DPDNet: Efficient channel expansion, Depthwise-Pointwise-Depthwise Inverted Bottleneck Block
Using depthwise convolution to expand channels yields networks with about 60 percent of MobileNetV2's parameters and comparable CIFAR accuracy.