Next Article in Journal
Fully Differential Miller Op-Amp with Enhanced Large- and Small-Signal Figures of Merit
Next Article in Special Issue
Implementation of a Fuel Estimation Algorithm Using Approximated Computing
Previous Article in Journal
Acknowledgment to Reviewers of Journal of Low Power Electronics and Applications in 2021
Previous Article in Special Issue
LoRaWAN Base Station Improvement for Better Coverage and Capacity
 
 
Article

CondenseNeXtV2: Light-Weight Modern Image Classifier Utilizing Self-Querying Augmentation Policies

Department of Electrical and Computer Engineering, Purdue School of Engineering and Technology, Indianapolis, IN 46254, USA
*
Author to whom correspondence should be addressed.
Academic Editor: Andrea Calimera
J. Low Power Electron. Appl. 2022, 12(1), 8; https://doi.org/10.3390/jlpea12010008
Received: 9 December 2021 / Revised: 17 January 2022 / Accepted: 21 January 2022 / Published: 3 February 2022
(This article belongs to the Special Issue Advanced Researches in Embedded Systems)
Artificial Intelligence (AI) combines computer science and robust datasets to mimic natural intelligence demonstrated by human beings to aid in problem-solving and decision-making involving consciousness up to a certain extent. From Apple’s virtual personal assistant, Siri, to Tesla’s self-driving cars, research and development in the field of AI is progressing rapidly along with privacy concerns surrounding the usage and storage of user data on external servers which has further fueled the need of modern ultra-efficient AI networks and algorithms. The scope of the work presented within this paper focuses on introducing a modern image classifier which is a light-weight and ultra-efficient CNN intended to be deployed on local embedded systems, also known as edge devices, for general-purpose usage. This work is an extension of the award-winning paper entitled ‘CondenseNeXt: An Ultra-Efficient Deep Neural Network for Embedded Systems’ published for the 2021 IEEE 11th Annual Computing and Communication Workshop and Conference (CCWC). The proposed neural network dubbed CondenseNeXtV2 utilizes a new self-querying augmentation policy technique on the target dataset along with adaption to the latest version of PyTorch framework and activation functions resulting in improved efficiency in image classification computation and accuracy. Finally, we deploy the trained weights of CondenseNeXtV2 on NXP BlueBox which is an edge device designed to serve as a development platform for self-driving cars, and conclusions will be extrapolated accordingly. View Full-Text
Keywords: CondenseNeXt; convolutional neural network; computer vision; embedded systems; edge devices; image classification; CNN; PyTorch CondenseNeXt; convolutional neural network; computer vision; embedded systems; edge devices; image classification; CNN; PyTorch
Show Figures

Figure 1

MDPI and ACS Style

Kalgaonkar, P.; El-Sharkawy, M. CondenseNeXtV2: Light-Weight Modern Image Classifier Utilizing Self-Querying Augmentation Policies. J. Low Power Electron. Appl. 2022, 12, 8. https://doi.org/10.3390/jlpea12010008

AMA Style

Kalgaonkar P, El-Sharkawy M. CondenseNeXtV2: Light-Weight Modern Image Classifier Utilizing Self-Querying Augmentation Policies. Journal of Low Power Electronics and Applications. 2022; 12(1):8. https://doi.org/10.3390/jlpea12010008

Chicago/Turabian Style

Kalgaonkar, Priyank, and Mohamed El-Sharkawy. 2022. "CondenseNeXtV2: Light-Weight Modern Image Classifier Utilizing Self-Querying Augmentation Policies" Journal of Low Power Electronics and Applications 12, no. 1: 8. https://doi.org/10.3390/jlpea12010008

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop