Deployment of Compressed MobileNet V3 on iMX RT 1060

dc.contributor.authorPrasad, S. P. Kavyashree
dc.contributor.authorEl-Sharkawy, Mohamed
dc.contributor.departmentElectrical and Computer Engineering, School of Engineering and Technologyen_US
dc.date.accessioned2023-01-20T22:10:57Z
dc.date.available2023-01-20T22:10:57Z
dc.date.issued2021-04
dc.description.abstractDeep Neural Networks (DNN) are prominent in most applications today. From self-driving cars, sentiment analysis, surveillance systems, and robotics, they have been used extensively. Among DNNs, Convolutional Neural Networks (CNN) have achieved massive success in computer vision applications as the human visual system inspires their architecture. However, striving to achieve higher accuracies, CNN complexity, parameters, and layers were increased, which led to a drastic surge in their size, making their deployment challenging. Over the years, many researchers have proposed various techniques to alleviate this issue-one of them being Design Space Exploration (DSE) to minimize size and computation with little compromise to accuracy. MobileNet V3 is one such architecture designed to achieve good accuracy while being mindful of resources. It produces an accuracy of 88.93% on CIFAR-10 with a size of 15.3MB. This paper further reduces its size to 2.3MB while boosting its accuracy to 89.13% using DSE techniques. It is then deployed into NXP's i.MX RT1060 Advanced Driver Assistance System (ADAS) platform.en_US
dc.eprint.versionAuthor's manuscripten_US
dc.identifier.citationPrasad, S. P. K., & El-Sharkawy, M. (2021). Deployment of Compressed MobileNet V3 on iMX RT 1060. 2021 IEEE International IOT, Electronics and Mechatronics Conference (IEMTRONICS), 1–4.en_US
dc.identifier.issn978-1-66544-067-7en_US
dc.identifier.urihttps://hdl.handle.net/1805/31002
dc.language.isoen_USen_US
dc.publisherIEEE Xploreen_US
dc.relation.isversionof10.1109/IEMTRONICS52119.2021.9422512en_US
dc.relation.journal2021 IEEE International IOT, Electronics and Mechatronics Conference (IEMTRONICS)en_US
dc.rightsPublisher Policyen_US
dc.sourceAuthoren_US
dc.subjectComputer architectureen_US
dc.subjectMechatronicsen_US
dc.subjectSentiment analysisen_US
dc.subjectVisual systemsen_US
dc.titleDeployment of Compressed MobileNet V3 on iMX RT 1060en_US
dc.typeArticleen_US
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Prasad2021Deployment-AAM.pdf
Size:
2.19 MB
Format:
Adobe Portable Document Format
Description:
Article
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.99 KB
Format:
Item-specific license agreed upon to submission
Description: