Viet-Anh on Software Logo

What is: Mixed Depthwise Convolution?

SourceMixConv: Mixed Depthwise Convolutional Kernels
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

MixConv, or Mixed Depthwise Convolution, is a type of depthwise convolution that naturally mixes up multiple kernel sizes in a single convolution. It is based on the insight that depthwise convolution applies a single kernel size to all channels, which MixConv overcomes by combining the benefits of multiple kernel sizes. It does this by partitioning channels into groups and applying a different kernel size to each group.