A-MnasNet and Image Classification on NXP Bluebox 2.0

Abstract

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.