A-MnasNet: Augmented MnasNet for Computer Vision

Shah, Prasham; El-Sharkawy, Mohamed

doi:10.1109/mwscas48704.2020.9184619

Cited by 4 publications

(9 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are constant learning rate algorithms and adaptive learning rate algorithms. For this research, Stochastic Gradient Descent optimizer [8] was used because of its enhanced performance on optimizing A-MnasNet [2]. It was used with varying values of learning rates during training with a momentum set to 0.9.…”

Section: Optimizationmentioning

confidence: 99%

“…This enables to develop autonomous applications. The vision processor and the compute processors are used to perform Image Classification [3] using A-MnasNet [2]. Figure 5 shows the methodology to deploy A-MnasNet[2] on Bluebox 2.0 for Image Classification.…”

Section: Data Augmentationmentioning

confidence: 99%

“…After training A-MnasNet [2], the model is imported in the RTMaps Studio using its python component. A TCP/IP connection is used for data transmission between RTMaps Design Studio and NXP Bluebox 2.0.…”

Section: Data Augmentationmentioning

confidence: 99%

“…This research aims to contribute towards this same goal, making CNNs compact in terms of model size and increasing its accuracy so that they can be used for such applications. [1] A-MnasNet [2] is derived by Design Space Exploration of Mnas-Net. New algorithms were implemented for more efficiency with competitive size and accuracy.…”

Section: Introductionmentioning

confidence: 99%

“…In this paper, section 2 discusses MnasNet architecture. Section 3 introduces A-MnasNet [2] and discusses the new algorithms implemented to achieve better results. Section 4 demonstrates deployment of A-MnasNet[2] on NXP Bluebox 2.0 for Image classification [3].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A-MnasNet and Image Classification on NXP Bluebox 2.0

Shah¹,

El-Sharkawy²

2021

Adv. sci. technol. eng. syst. j.

Self Cite

View full text Add to dashboard Cite

Computer Vision is a domain which deals with the challenge of enabling technology with vision capabilities. This goal is accomplished with the use of Convolutional Neural Networks. They are the backbone of implementing vision applications on embedded systems. They are complex but highly efficient in extracting features, thus, enabling embedded systems to perform computer vision applications. After AlexNet won the ImageNet Large Scale Visual Recognition Challenge in 2012, there was a drastic increase in research on Convolutional Neural Networks. The convolutional neural networks were made deeper and wider, in order to make them more efficient. They were able to extract features efficiently, but the computational complexity and the computational cost of those networks also increased. It became very challenging to deploy such networks on embedded hardware. Since embedded systems have limited resources like power, speed and computational capabilities, researchers got more inclined towards the goal of making convolutional neural networks more compact, with efficiency of extracting features similar to that of the novel architectures. This research has a similar goal of proposing a convolutional neural network with enhanced efficiency and further using it for a vision application like Image Classification on NXP Bluebox 2.0, an autonomous driving platform by NXP Semiconductors. This paper gives an insight on the Design Space Exploration technique used to propose A-MnasNet (Augmented MnasNet) architecture, with enhanced capabilities, from MnasNet architecture. Furthermore, it explains the implementation of A-MnasNet on Bluebox 2.0 for Image Classification.

show abstract

Section: Optimizationmentioning

confidence: 99%

Section: Data Augmentationmentioning

confidence: 99%

Section: Data Augmentationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations