Viet-Anh on Software Logo

What is: Depthwise Separable Convolution?

SourceXception: Deep Learning With Depthwise Separable Convolutions
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

While standard convolution performs the channelwise and spatial-wise computation in one step, Depthwise Separable Convolution splits the computation into two steps: depthwise convolution applies a single convolutional filter per each input channel and pointwise convolution is used to create a linear combination of the output of the depthwise convolution. The comparison of standard convolution and depthwise separable convolution is shown to the right.

Credit: Depthwise Convolution Is All You Need for Learning Multiple Visual Domains