ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design

Ningning Ma; Xiangyu Zhang; Hai-Tao Zheng; Jian Sun

ECCV 2018poster7574 citations

ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design

Ningning Ma, Xiangyu Zhang, Hai-Tao Zheng, Jian Sun

Abstract

Current network architecture design is mostly guided by the indirect metric of computation complexity, i.e., FLOPs. However, the direct metric, such as speed, also depends on the other factors such as memory access cost and platform characterics. Taking these factors into account, this work proposes practical guidelines for efficient network de- sign. Accordingly, a new architecture called ShuffleNet V2 is presented. Comprehensive experiments verify that it is the state-of-the-art in both speed and accuracy.

BibTeX

@inproceedings{eccv2018_shufflenetv2prac,
  title = {ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design},
  author = {Ningning Ma and Xiangyu Zhang and Hai-Tao Zheng and Jian Sun},
  booktitle = {ECCV 2018},
  year = {2018}
}