Decouple and Stretch : A Boost to Channel Pruning

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review

1 Scopus Citations
View graph of relations

Author(s)

Detail(s)

Original languageEnglish
Title of host publication2018 IEEE 37th International Performance Computing and Communications Conference (IPCCC)
PublisherIEEE
Number of pages6
ISBN (Electronic)9781538668085
ISBN (Print)9781538668092
Publication statusPublished - Nov 2018
Externally publishedYes

Publication series

Name
ISSN (Print)1097-2641
ISSN (Electronic)2374-9628

Conference

Title37th IEEE International Performance Computing and Communications Conference (IPCCC 2018)
Location
PlaceUnited States
CityOrlando
Period17 - 19 November 2018

Abstract

Deep Neural Networks (DNNs) have shown superior performance on a variety of artificial intelligence problems. Reducing the resource usage of DNN is critical to adding intelligence on Internet of Things (IoT) devices. Channel pruning based network compression shows effective reduction simultaneously on storage, memory and computation without specialized software on general platforms. But limited by pruning flexibility, channel pruning methods have relatively low compression rate for a given target performance. In this paper, we demonstrate that channel pruning becomes more robust to decision errors by reducing the granularity of filters. Then we propose a Decouple and Stretch (DS) scheme to enhance channel pruning. Under this scheme, each filter in a specific layer is decoupled into two small spatial-wise filters, and the spatial-wise filters are stretched into two successive convolutional layers. Our scheme obtains up to 49% improvement on compression and 35% improvement on acceleration. To further demonstrate hardware compatibility, we deploy pruned networks on the FPGA, and the network produced by Decouple and Stretch scheme is more hardware-friendly with latency reduced by 42%.

Research Area(s)

  • deep learning, Internet of Things, network compression, channel pruning, hardware resources

Citation Format(s)

Decouple and Stretch : A Boost to Channel Pruning. / Chen, Zhen; Lin, Jianxin; Liu, Sen; Xia, Jun; Li, Weiping.

2018 IEEE 37th International Performance Computing and Communications Conference (IPCCC). IEEE, 2018. 8711260.

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review