Depthwise Separable Convolution

Introduced by Chollet in Xception: Deep Learning With Depthwise Separable Convolutions

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

Source: Xception: Deep Learning With Depthwise Separable Convolutions


Paper Code Results Date Stars


Task Papers Share
Image Classification 73 10.64%
Object Detection 51 7.43%
Classification 40 5.83%
Quantization 34 4.96%
Semantic Segmentation 30 4.37%
Decoder 11 1.60%
Instance Segmentation 11 1.60%
Management 9 1.31%
Ensemble Learning 8 1.17%