Improved inception-residual convolutional neural network for object recognition
Improved inception-residual convolutional neural network for object recognition
复制标题
DOI：
10.1007/s00521-018-3627-6
复制
发表时间：
2020-01-01
影响因子：
6
通讯作者：
Asari, Vijayan K.
中科院分区：
文献类型：
--
作者：
Alom, Md Zahangir;Hasan, Mahmudul;Asari, Vijayan K.
机器学习和计算机视觉推动了深度卷积神经网络(DCNN)建模的许多最大进展。目前，大多数研究都集中在通过更好的DCNN模型和学习方法来提高识别准确率。除了在几个DCNN结构中应用之外，递归卷积方法并不是很常用。另一方面，盗梦空间v4和残差网络迅速在计算机视觉界流行起来。本文介绍了一种新的DCNN模型，称为初始递归残差卷积神经网络(IRRCNN)，它利用了递归卷积神经网络(RCNN)、初始网络和残差网络的能力。该方法在网络参数相同的情况下，提高了初始残差网络的识别精度。此外，该体系结构对初始网络、RCNN和残差网络进行了泛化，显著提高了训练精度。我们对IRRCNN模型在CIFAR-10、CIFAR-100、TinyImageNet-200和CU3D-100等不同基准上的性能进行了实证评估。实验结果表明，对于大多数流行的DCNN模型，包括RCNN，都有较高的识别率。我们还研究了IRRCNN方法在CIFAR-100数据集上相对于等价初始网络(EIN)和等效初始残差网络(EIRN)的性能。我们报告说，在CIFAR-100数据集上，与RCNN、EIN和EIRN相比，分类准确率分别提高了4.53%、4.49%和3.56%。此外，在TinyImageNet-200和CU3D-100数据集上进行了实验，其中IRRCNN比初始重复CNN、EIN、EIRN、初始-v3和宽剩余网络提供了更好的测试精度。
Machine learning and computer vision have driven many of the greatest advances in the modeling of Deep Convolutional Neural Networks (DCNNs). Nowadays, most of the research has been focused on improving recognition accuracy with better DCNN models and learning approaches. The recurrent convolutional approach is not applied very much, other than in a few DCNN architectures. On the other hand, Inception-v4 and Residual networks have promptly become popular among computer the vision community. In this paper, we introduce a new DCNN model called the Inception Recurrent Residual Convolutional Neural Network (IRRCNN), which utilizes the power of the Recurrent Convolutional Neural Network (RCNN), the Inception network, and the Residual network. This approach improves the recognition accuracy of the Inception-residual network with same number of network parameters. In addition, this proposed architecture generalizes the Inception network, the RCNN, and the Residual network with significantly improved training accuracy. We have empirically evaluated the performance of the IRRCNN model on different benchmarks including CIFAR-10, CIFAR-100, TinyImageNet-200, and CU3D-100. The experimental results show higher recognition accuracy against most of the popular DCNN models including the RCNN. We have also investigated the performance of the IRRCNN approach against the Equivalent Inception Network (EIN) and the Equivalent Inception Residual Network (EIRN) counterpart on the CIFAR-100 dataset. We report around 4.53, 4.49 and 3.56% improvement in classification accuracy compared with the RCNN, EIN, and EIRN on the CIFAR-100 dataset respectively. Furthermore, the experiment has been conducted on the TinyImageNet-200 and CU3D-100 datasets where the IRRCNN provides better testing accuracy compared to the Inception Recurrent CNN, the EIN, the EIRN, Inception-v3, and Wide Residual Networks.