Skip to main navigation Skip to search Skip to main content

Prune it Yourself: Automated Pruning by Multiple Level Sensitivity

  • Peking University
  • Pengcheng Laboratory

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Deep neural network pruning is to reduce the model size by removing redundant structures and weights. Existing methods focus on single layer information which ignore other layers. And pruning progress is simply removing all weights at the same time. To address these limitations, we propose Prune it Yourself (PIY) framework. First, we collect both filter and channel sensitivity information. Then combine them to decide the structure to be pruned. At last we use the gradual pruning algorithm to reduce the accuracy loss without extra hyper-parameters. We use VGG-16 and ResNet to perform experiments on CIFAR-10 and ImageNet. The experimental results prove the effectiveness of our method.

Original languageEnglish
Title of host publicationProceedings - 3rd International Conference on Multimedia Information Processing and Retrieval, MIPR 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages73-78
Number of pages6
ISBN (Electronic)9781728142722
DOIs
StatePublished - Aug 2020
Externally publishedYes
Event3rd International Conference on Multimedia Information Processing and Retrieval, MIPR 2020 - Shenzhen, Guangdong, China
Duration: 6 Aug 20208 Aug 2020

Publication series

NameProceedings - 3rd International Conference on Multimedia Information Processing and Retrieval, MIPR 2020

Conference

Conference3rd International Conference on Multimedia Information Processing and Retrieval, MIPR 2020
Country/TerritoryChina
CityShenzhen, Guangdong
Period6/08/208/08/20

Keywords

  • deep neural network
  • model compression
  • pruning

Fingerprint

Dive into the research topics of 'Prune it Yourself: Automated Pruning by Multiple Level Sensitivity'. Together they form a unique fingerprint.

Cite this