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 87 12.24%
Object Detection 59 8.30%
Classification 37 5.20%
Semantic Segmentation 34 4.78%
Quantization 33 4.64%
General Classification 24 3.38%
Model Compression 12 1.69%
Knowledge Distillation 10 1.41%
Multi-Task Learning 10 1.41%