Pulse-Net: Dynamic Compression of Convolutional Neural Networks
Publication Type:
Refereed Conference Meeting Proceeding
Abstract:
Convolutional Neural Networks (CNNs) are used in
a range of computer vision tasks, with state-of-the-art CNNs
such as AlexNet and VGG16 constructed using a large number
of parameter and multiply-add operations (MACs). These tasks
require high computational power and high energy requirements
to run the CNNs, making them unsuitable for deployment on Internet
of Things devices. To overcome this issue and facilitate the
use of CNNs on these resource-constrained devices, compression
technology through pruning research has gained momentum and
is an important tool for improving performance during inference.
Our work focuses on pruning unwanted filters and nodes in all
layers of a network. The network is pruned iteratively during
training via a novel approach we call Pulse-Net, and a significant
number of filters/nodes are removed while ensuring any loss
in accuracy is within a predetermined range. The unpruned
network can be extracted from the original structure for the
inference stage. This novel method has an easy-to-set parameter
to control the trade-off between accuracy and compression. Pulse-
Net gives greater compression, while maintaining competitive accuracy
loss, than other reported methods like, efficient convnets,
ThiNet and Cross-Entropy Pruning. It also has better robustness
against adversarial attacks than other compression and pruning
techniques.
Conference Name:
IEEE IoT World Forum 2019
Proceedings:
https://ieeexplore.ieee.org
Digital Object Identifer (DOI):
10.1109/WF-IoT.2019.8767300
Publication Date:
18/04/2019
Conference Location:
Ireland
Research Group:
Institution:
National University of Ireland, Cork (UCC)
Open access repository:
Yes
Publication document: