当前位置: X-MOL 学术Mach. Vis. Appl. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Inception recurrent convolutional neural network for object recognition
Machine Vision and Applications ( IF 2.4 ) Pub Date : 2021-01-03 , DOI: 10.1007/s00138-020-01157-3
Md Zahangir Alom , Mahmudul Hasan , Chris Yakopcic , Tarek M. Taha , Vijayan K. Asari

Deep convolutional neural network (DCNN) is an influential tool for solving various problems in machine learning and computer vision. Recurrent connectivity is a very important component of visual information processing within the human brain. The idea of recurrent connectivity is rarely applied within convolutional layers, the exceptions being a couple of DCNN architectures including recurrent convolutional neural network (RCNN) in Liang and Hu (in: Proceedings of the IEEE conference on computer vision and pattern recognition, 2015) and Pinheiro and Collobert (in: ICML, 2014). On the other hand, the Inception network architecture has become popular among the computer vision community (Szegedy et al. in Inception-v4, Inception-ResNet and the impact of Residual connections on learning, 2016. arXiv:1602.07261). In this paper, we introduce a deep learning architecture called the Inception Recurrent Convolutional Neural Network (IRCNN), which utilizes the power of an Inception network combined with recurrent convolutional layers. Although the inputs are static, the recurrent property plays a huge role in modeling the contextual information for object recognition tasks and thus improves overall training and testing accuracy. In addition, this proposed architecture generalizes both Inception and RCNN models. We have empirically evaluated the recognition performance of the proposed IRCNN model using different benchmark datasets such as MNIST, CIFAR-10, CIFAR-100, and SVHN. The experimental results show higher recognition accuracy when compared to most of the popular DCNNs including the RCNN. Furthermore, we have investigated IRCNN performance against equivalent Inception networks (EIN) and equivalent Inception–Residual networks (EIRN) using the CIFAR-100 dataset. When using the augmented CIFAR-100 dataset, we achieved about 3.5%, 3.47% and 2.54% improvement in classification accuracy compared to the RCNN, EIN, and EIRN respectively. We have also conducted experiment on Tiny ImageNet-200 dataset with IRCNN, EIN, EIRN, RCNN, DenseNet in Huang et al. (Densely connected convolutional networks, 2016. arXiv:1608.06993), and DenseNet with Recurrent Convolution Layer, where the proposed model shows significantly better performance against baseline models.



中文翻译:

初始循环卷积神经网络用于目标识别

深度卷积神经网络(DCNN)是解决机器学习和计算机视觉中各种问题的有力工具。循环连接是人脑中视觉信息处理的非常重要的组成部分。循环连接的想法很少在卷积层中应用,例外是几个DCNN架构,包括Liang和Hu中的循环卷积神经网络(RCNN)(见:IEEE计算机视觉和模式识别会议论文集,2015年)和Pinheiro和Collobert(在:ICML,2014年)。另一方面,Inception网络体系结构已在计算机视觉社区中流行(Szegedy等人,在Inception-v4,Inception-ResNet和残差连接对学习的影响中,2016年。arXiv:1602.07261)。在本文中,我们介绍了一种称为Inception递归卷积神经网络(IRCNN)的深度学习架构,该架构利用了Inception网络与递归卷积层相结合的功能。尽管输入是静态的,但递归属性在为对象识别任务建模上下文信息方面发挥着巨大作用,因此提高了整体训练和测试的准确性。另外,该提议的体系结构概括了Inception模型和RCNN模型。我们使用不同的基准数据集(例如MNIST,CIFAR-10,CIFAR-100和SVHN)以经验方式评估了所提出的IRCNN模型的识别性能。与大多数流行的DCNN(包括RCNN)相比,实验结果显示出更高的识别精度。此外,我们使用CIFAR-100数据集研究了IRCNN针对等效Inception网络(EIN)和等效Inception-残差网络(EIRN)的性能。使用增强的CIFAR-100数据集时,与RCNN,EIN和EIRN相比,我们分别实现了约3.5%,3.47%和2.54%的分类准确率改善。我们还用Huang等人的IRCNN,EIN,EIRN,RCNN,DenseNet在Tiny ImageNet-200数据集上进行了实验。(密集连接的卷积网络,2016年。arXiv:1608.06993),以及具有循环卷积层的DenseNet,其中所提出的模型相对于基线模型表现出明显更好的性能。与RCNN,EIN和EIRN相比,分类准确性分别提高了54%。我们还用Huang等人的IRCNN,EIN,EIRN,RCNN,DenseNet在Tiny ImageNet-200数据集上进行了实验。(密集连接的卷积网络,2016年。arXiv:1608.06993),以及具有循环卷积层的DenseNet,其中所提出的模型相对于基线模型表现出明显更好的性能。与RCNN,EIN和EIRN相比,分类准确性分别提高了54%。我们还用Huang等人的IRCNN,EIN,EIRN,RCNN,DenseNet在Tiny ImageNet-200数据集上进行了实验。(密集连接的卷积网络,2016年。arXiv:1608.06993),以及具有循环卷积层的DenseNet,其中所提出的模型相对于基线模型表现出明显更好的性能。

更新日期:2021-01-03
down
wechat
bug