Thin MobileNet: An Enhanced MobileNet Architecture

If you need an accessible version of this item, please email your request to digschol@iu.edu so that they may create one and provide it to you.
Date
2019-10
Language
English
Embargo Lift Date
Committee Members
Degree
Degree Year
Department
Grantor
Journal Title
Journal ISSN
Volume Title
Found At
IEEE
Abstract

In the field of computer, mobile and embedded vision Convolutional Neural Networks (CNNs) are deep learning models which play a significant role in object detection and recognition. MobileNet is one such efficient, light-weighted model for this purpose, but there are many constraints or challenges for the hardware deployment of such architectures into resource-constrained micro-controller units due to limited memory, energy and power. Also, the overall accuracy of the model generally decreases when the size and the total number of parameters are reduced by any method such as pruning or deep compression. The paper proposes three hybrid MobileNet architectures which has improved accuracy along-with reduced size, lesser number of layers, lower average computation time and very less overfitting as compared to the baseline MobileNet v1. The reason behind developing these models is to have a variant of the existing MobileNet model which will be easily deployable in memory constrained MCUs. We name the model having the smallest size (9.9 MB) as Thin MobileNet. We achieve an increase in accuracy by replacing the standard non-linear activation function ReLU with Drop Activation and introducing Random erasing regularization technique in place of drop out. The model size is reduced by using Separable Convolutions instead of the Depthwise separable convolutions used in the baseline MobileNet. Later on, we make our model shallow by eliminating a few unnecessary layers without a drop in the accuracy. The experimental results are based on training the model on CIFAR-10 dataset.

Description
item.page.description.tableofcontents
item.page.relation.haspart
Cite As
Sinha, D., & El-Sharkawy, M. (2019). Thin MobileNet: An Enhanced MobileNet Architecture. 2019 IEEE 10th Annual Ubiquitous Computing, Electronics Mobile Communication Conference (UEMCON), 0280–0285. https://doi.org/10.1109/UEMCON47517.2019.8993089
ISSN
Publisher
Series/Report
Sponsorship
Major
Extent
Identifier
Relation
Journal
2019 IEEE 10th Annual Ubiquitous Computing, Electronics Mobile Communication Conference (UEMCON)
Source
Author
Alternative Title
Type
Conference proceedings
Number
Volume
Conference Dates
Conference Host
Conference Location
Conference Name
Conference Panel
Conference Secretariat Location
Version
Author's manuscript
Full Text Available at
This item is under embargo {{howLong}}