Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications

By Yong-Deok Kim, Eunhyeok Park, Sungjoo Yoo, Taelim Choi, Lu Yang, Dongjun Shin. 2015

949 citations recorded by the source corpus.

Although the latest high-end smartphone has powerful CPU and GPU, running deeper convolutional neural networks (CNNs) for complex tasks such as ImageNet classification on mobile devices is challenging. To deploy deep CNNs on mobile devices, we present a simple and effective scheme to compress the entire CNN, which we call one-shot whole network compression. The proposed scheme consists of three steps: (1) rank selection with variational Bayesian matrix factorization, (2) Tucker decomposition on kernel tensor, and (3) fine-tuning to recover accumulated loss of accuracy, and each step can be easily implemented using publicly available tools. We demonstrate the effectiveness of the proposed scheme by testing the performance of various compressed CNNs (AlexNet, VGGS, GoogLeNet, and VGG-16) on the smartphone. Significant reductions in model size, runtime, and energy consumption are obtained, at the cost of small loss in accuracy. In addition, we address the important implementation level issue on 1?1 convolution, which is a key operation of inception module of GoogLeNet as well as CNNs compressed by our proposed scheme.

Subfields: Computational Mathematics, Computer Vision and Pattern Recognition, 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 Computational Mathematics

  1. Qiang Yang
  2. Timothy M. Hospedales
  3. Jean Kossaifi
  4. Yongxin Yang
  5. Yi-Zhe Song
  6. Da Li
  7. Zachary Chase Lipton
  8. Yang He

In Computer Vision and Pattern Recognition

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

In Efficiency & Compression

  1. Song Han
  2. Yang He
  3. Ji Lin
  4. Tijmen Blankevoort
  5. Dan Alistarh
  6. Jonathan Frankle
  7. Dacheng Tao
  8. Yunhe Wang

Citations in the corpus