ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design

By Ningning Ma, Xiangyu Zhang, Haitao Zheng. 2018

6,472 citations recorded by the source corpus.

Currently, the neural network architecture design is mostly guided by the indirect metric of computation complexity, i.e., FLOPs. However, the direct metric, e.g., speed, also depends on the other factors such as memory access cost and platform characterics. Thus, this work proposes to evaluate the direct metric on the target platform, beyond only considering FLOPs. Based on a series of controlled experiments, this work derives several practical guidelines for efficient network design. Accordingly, a new architecture is presented, called ShuffleNet V2. Comprehensive ablation experiments verify that our model is the state-of-the-art in terms of speed and accuracy tradeoff.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Neurology, Efficiency & Compression

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Quoc V. Le
  2. Dacheng Tao
  3. Jianfeng Gao
  4. Mohit Bansal
  5. Yoshua Bengio
  6. Trevor Darrell
  7. Jiashi Feng
  8. Percy Liang

In Computer Vision and Pattern Recognition

  1. Luc Van Gool
  2. Dacheng Tao
  3. Ming-Hsuan Yang
  4. Xiaogang Wang
  5. Trevor Darrell
  6. Chunhua Shen
  7. Alan L. Yuille
  8. Yi Yang

In Neurology

  1. Song Han
  2. Chunhua Shen
  3. X. Zhang
  4. Jiashi Feng
  5. Kaiming He
  6. Hongpeng Liao
  7. Chien-Yao Wang
  8. Xiaogang Wang

In Efficiency & Compression

  1. Song Han
  2. Kurt Keutzer
  3. Quoc V. Le
  4. Chuang Gan
  5. Thomas S. Huang
  6. Jiahui Yu
  7. Ji Lin
  8. Mingxing Tan

Citations in the corpus