Deep neural networks are increasingly used in many fields, such as pattern recognition, computer vision, and natural language processing. However, how to apply deep neural networks in mobile settings has become an urgent issue, as mobile devices are getting more and more popularity. This is mainly due to the fact that mobile devices usually have very limited computation and storage resources, which prevents from running a large-scale deep network. This paper proposes a novel method for structure compression of deep neural networks. The main idea is to merge the neurons and connections of the original network using clustering methods. To the end, the new network after compression possesses much less parameters, which leads to reduced requirements for computation and storage resources. Experiments on benchmark data sets demonstrate that the proposed method can greatly improve the efficiency of deep neural networks, while retain their learning capability.
|Title of host publication||2018 24th International Conference on Pattern Recognition, ICPR 2018|
|Publisher||Institute of Electrical and Electronics Engineers Inc.|
|Number of pages||6|
|Publication status||Published - 29 Nov 2018|
|Event||24th International Conference on Pattern Recognition, ICPR 2018 - Beijing, China|
Duration: 20 Aug 2018 → 24 Aug 2018
|Name||Proceedings - International Conference on Pattern Recognition|
|Conference||24th International Conference on Pattern Recognition, ICPR 2018|
|Period||20/08/2018 → 24/08/2018|
Bibliographical noteFunding Information:
This work was supported by the National Key R&D Program of China under Grant 2016YFC1401004, the Science and Technology Program of Qingdao under Grant No. 17-3-3-20-nsh, the CERNET Innovation Project under Grant No. NGI-I20170416, the CCF-Tencent Open Fund, the UK EPSRC under Grants EP/N508664/1, EP/R007187/1 and EP/N011074/1, the Royal Society-Newton Advanced Fellowship under Grant NA160342, and the Fundamental Research Funds for the Central Universities of China.
© 2018 IEEE.
Copyright 2019 Elsevier B.V., All rights reserved.
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition