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 ConvolutionsPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Image Classification | 78 | 11.56% |
Object Detection | 51 | 7.56% |
Classification | 40 | 5.93% |
Quantization | 34 | 5.04% |
Semantic Segmentation | 30 | 4.44% |
Instance Segmentation | 11 | 1.63% |
Management | 9 | 1.33% |
Ensemble Learning | 8 | 1.19% |
Computational Efficiency | 8 | 1.19% |