Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
6-2018
Abstract
The emergence of augmented reality devices such as Google Glass and Microsoft Hololens has opened up a new class of vision sensing applications. Those applications often require the ability to continuously capture and analyze contextual information from video streams. They often adopt various deep learning algorithms such as convolutional neural networks (CNN) to achieve high recognition accuracy while facing severe challenges to run computationally intensive deep learning algorithms on resource-constrained mobile devices. In this paper, we propose and explore a new class of compression technique called D-Pruner to efficiently prune redundant parameters within a CNN model to run the model efficiently on mobile devices. D-Pruner removes redundancy by embedding a small additional network. This network evaluates the importance of filters and removes them during the fine-tuning phase to efficiently reduce the size of the model while maintaining the accuracy of the original model. We evaluated D-Pruner on various datasets such as CIFAR-10 and CIFAR-100 and showed that D-Pruner could reduce a significant amount of parameters up to 4.4 times on many existing models while maintaining accuracy drop less than 1%.
Keywords
Compression, Deep Learning, Continuous Vision
Discipline
Software Engineering
Research Areas
Software and Cyber-Physical Systems
Publication
EMDL'18: Proceedings of the 2nd International Workshop on Embedded and Mobile Deep Learning, Munich, Germany, June 15
First Page
7
Last Page
12
ISBN
9781450358446
Identifier
10.1145/3212725.3212730
Publisher
ACM
City or Country
New York
Citation
HUYNH, Nguyen Loc; LEE, Youngki; and BALAN, Rajesh Krishna.
D-pruner: Filter-based pruning method for deep convolutional neural network. (2018). EMDL'18: Proceedings of the 2nd International Workshop on Embedded and Mobile Deep Learning, Munich, Germany, June 15. 7-12.
Available at: https://ink.library.smu.edu.sg/sis_research/4204
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.1145/3212725.3212730