Depthwise Convolution

Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D convolution performed over multiple input channels, the filter is as deep as the input and lets us freely mix channels to generate each element in the output. In contrast, depthwise convolutions keep each channel separate. To summarize the steps, we:

  1. Split the input and filter into channels.
  2. We convolve each input with the respective filter.
  3. We stack the convolved outputs together.

Image Credit: Chi-Feng Wang


Paper Code Results Date Stars


Task Papers Share
Image Classification 82 12.62%
Object Detection 52 8.00%
Quantization 35 5.38%
Semantic Segmentation 35 5.38%
Classification 34 5.23%
Instance Segmentation 11 1.69%
Model Compression 10 1.54%
Benchmarking 9 1.38%
Edge-computing 8 1.23%


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign