Authors: Hussein A. Al-Barazanchi; Hussam Qassim; Abhishek Verma
Addresses: Department of Computer Science, California State University, Fullerton, California 92834, USA ' Department of Computer Science, California State University, Fullerton, California 92834, USA ' Department of Computer Science, New Jersey City University, Jersey City, NJ 07305, USA
Abstract: Increasing depth of convolutional neural networks (CNNs) is a highly promising method of increasing the accuracy of the (CNNs). Increased CNN depth will also result in increased layer count (parameters), leading to a slow backpropagation convergence prone to overfitting. We trained our model (residual-CNDS) to classify very large-scale scene datasets. The outcome result from the two datasets proved our proposed model effectively handled the slow convergence, overfitting, and degradation. Our approach overcomes degradation in the very deep network. We have built two models (residual-CNDS 8), and (residual-CNDS 10). Moreover, we tested our models on two large-scale datasets, and we compared our results with other recently introduced cutting-edge networks in the domain of top-1 and top-5 classification accuracy. As a result, both of models have shown good improvement, which supports the assertion that the addition of residual connections enhances network CNDS accuracy without adding any computation complexity.
Keywords: residual-CNDS; scene classification; residual learning convolutional neural networks to residual learning; convolutional networks with deep supervision.
International Journal of Computational Vision and Robotics, 2020 Vol.10 No.3, pp.185 - 201
Received: 20 Aug 2018
Accepted: 22 Apr 2019
Published online: 29 Apr 2020 *