ShuffleNet

2000년 도입 · 논문 51편에서 사용

ShuffleNet is a convolutional neural network designed specially for mobile devices with very limited computing power. The architecture utilizes two new operations, pointwise group convolution and channel shuffle, to reduce computation cost while maintaining accuracy.

출처: ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices

소개 논문: ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices