A Comprehensive Study of Deep Learning and Performance Comparison of Deep Neural Network Models (YOLO, RetinaNet)

Nadia Ibrahim Nife; Mohammed Chtourou

doi:10.3991/ijoe.v19i12.42607

Authors

Nadia Ibrahim Nife University of Kirkuk, Kirkuk, Iraq, Control & Energy Management Laboratory, National School of Sfax Engineers (ENIS), University of Sfax, Sfax, Tunisia
Mohammed Chtourou Control & Energy Management Laboratory, National School of Sfax Engineers (ENIS), University of Sfax, Sfax, Tunisia

DOI:

https://doi.org/10.3991/ijoe.v19i12.42607

Keywords:

Deep learning, neural networks, big data, object detection; convolutional neural network (CNN), YOLO model, RetinaNet model.

Abstract

This paper presents the latest advances in machine learning techniques and highlights deep learning (DL) methods in recent studies. This technology has recently received great attention as it can solve complex problems. This paper focuses on covering one of the deep learning algorithms (deep neural network) and learning about its types such as convolutional neural network (CNN), Recurrent Neural Networks (RNN), etc. We have discussed recent changes, such as advanced DL technologies. Next, we continue analyzing and discussing the challenges and possible solutions of machine learning, such as big data and object detection, studying more papers in deep learning, and knowing the main experiments and future directions. In addition, this review also identifies some successful deep learning applications in recent years. Moreover, in this paper, one of the deep learning methods, convolutional neural networks, is applied to detect objects in images by using the You Only Look One model and comparing it with RetinaNet using pre-trained models. The results found that CNN (using YOLOv3) is a more accurate model than RetinaNet.