Open AccessComparison of Convolutional Neural Network Models for Mobile Devices
Author(s) -
Vivian Kimie Isuyama,
Bruno De Carvalho Albertini
Publication year - 2021
Language(s) - English
Resource type - Conference proceedings
DOI - 10.5753/wperformance.2021.15724
Subject(s) - computer science , convolutional neural network , mobile device , inference , task (project management) , artificial intelligence , computational complexity theory , mobile computing , contextual image classification , artificial neural network , image (mathematics) , architecture , deep learning , machine learning , pattern recognition (psychology) , computer network , algorithm , engineering , art , visual arts , systems engineering , operating system
In recent years mobile devices have become an important part of our daily lives and Deep Convolutional Neural Networks have been performing well in the task of image classification. Some considerations have to be made when running a Neural Network inside a mobile device such as computational complexity and storage size. In this paper, common architectures for image classification were analyzed to retrieve the values of accuracy rate, model complexity, memory usage, and inference time. Those values were compared and it was possible to show which architecture to choose from considering mobile restrictions.