Pointwise Convolution

2016년 도입 · 논문 1,306편에서 사용

Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This kernel has a depth of however many channels the input image has. It can be used in conjunction with depthwise convolutions to produce an efficient class of convolutions known as depthwise-separable convolutions. Image Credit: Chi-Feng Wang