基于分组模块的卷积神经网络设计
|
摘要
本文提出了一种基于分组模块的卷积结构,先将输出特征图分成数量相等的两组,每一组采用不同的卷积核进行操作以提取更充分的信息,而后将分组得到的多样性特征图像进行级联,最后通过1*1的卷积核将所有特征图整合.与传统的CNN比较,使用本文模块的网络在数据集Caltech256上将识别率由50.1%提升至52.2%.在数据集101_food上将识别精度由66.3%提升至68.9%.实验结果表明网络在识别精度性能上有所提升.
This paper proposes a grouping method of convolution structure for feature extraction of images.The model increases the depth of network,and the network parameters changes smaller.Compared with the traditional CNN,the network using the module of this paper increases the recognition rate from 50.1% to 52.2% on the data set Caltech256.On the data set 101_food,the recognition accuracy increased from 66.3% to 68.9%.Experimental results show that the network structure in the paper improves the network performance.
This paper proposes a grouping method of convolution structure for feature extraction of images.The model increases the depth of network,and the network parameters changes smaller.Compared with the traditional CNN,the network using the module of this paper increases the recognition rate from 50.1% to 52.2% on the data set Caltech256.On the data set 101_food,the recognition accuracy increased from 66.3% to 68.9%.Experimental results show that the network structure in the paper improves the network performance.
引文
[1] Hinton G E,Salakhutdinov R R.Reducing the Dimensionality of Data with Neural Networks[J].Science,2006,313(5786):504.
[2]Lecuny,Bottou L,Bengio Y,et al.Geadient-based learning applied to document recognition[J].Pr Oceeding of the IEEE,1998,86(11);2278-2324.
[3]杨远飞,曾上游.基于并行和切片的深度卷积网络设计研究[J].微电子学与计算机,2018,35(3):120-124.
[4] Ioffe S,Szegedy C.Batch normalization:accelerating deep network training by reducing internal covariate shift[C]∥International Conference on International Conference on Machine Learning.JMLR.org,2015.
[5]周飞燕,金林鹏.卷积神经网络研究综述[J].计算机学报,2017,40(6):1229-1251.
[6]杨天祺,黄双喜.改进卷积神经网络在分类与推荐中的实例应用[J].计算机应用研究,2018,35(4):974-977.
[7]张顺,龚怡宏.深度卷积神经网络的发展及其在计算机视觉领域的应用[J].计算机学报,2017(9).
[8] Jia Y,Shelhamer E,Donahue J,et al.Caffe:Convolutional Architecture for Fast Feature Embedding[C]∥ACM International Conference on Multimedia.ACM,2014:675-678.
[9] Krizhevsky A,Sutskever I,Hinton G E.Imagenet classification with deep convolutional neural networks[C]∥Advances in Neural Information Processing Systems.2012:1097-1105.
[10]Krizhevsky A,Sutskever I,Hinton G E.ImageNet classification with deep convolutional neural networks[C]∥International Conference on Neural Information Processing Systems.Curran Associates Inc.2012:1097-1105.
[2]Lecuny,Bottou L,Bengio Y,et al.Geadient-based learning applied to document recognition[J].Pr Oceeding of the IEEE,1998,86(11);2278-2324.
[3]杨远飞,曾上游.基于并行和切片的深度卷积网络设计研究[J].微电子学与计算机,2018,35(3):120-124.
[4] Ioffe S,Szegedy C.Batch normalization:accelerating deep network training by reducing internal covariate shift[C]∥International Conference on International Conference on Machine Learning.JMLR.org,2015.
[5]周飞燕,金林鹏.卷积神经网络研究综述[J].计算机学报,2017,40(6):1229-1251.
[6]杨天祺,黄双喜.改进卷积神经网络在分类与推荐中的实例应用[J].计算机应用研究,2018,35(4):974-977.
[7]张顺,龚怡宏.深度卷积神经网络的发展及其在计算机视觉领域的应用[J].计算机学报,2017(9).
[8] Jia Y,Shelhamer E,Donahue J,et al.Caffe:Convolutional Architecture for Fast Feature Embedding[C]∥ACM International Conference on Multimedia.ACM,2014:675-678.
[9] Krizhevsky A,Sutskever I,Hinton G E.Imagenet classification with deep convolutional neural networks[C]∥Advances in Neural Information Processing Systems.2012:1097-1105.
[10]Krizhevsky A,Sutskever I,Hinton G E.ImageNet classification with deep convolutional neural networks[C]∥International Conference on Neural Information Processing Systems.Curran Associates Inc.2012:1097-1105.