Depthwise Separable Convolution

2000년 도입 · 논문 1,174편에서 사용

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

출처: Xception: Deep Learning With Depthwise Separable Convolutions

소개 논문: Xception: Deep Learning With Depthwise Separable Convolutions