A Lightweight Convolutional Neural Network Architecture with Slice Feature Map

被引：0

作者：

Zhang Y. ^{[1
]}

Zheng Z. ^{[1
]}

Liu H. ^{[1
]}

Xiang D. ^{[2
]}

He X. ^{[1
]}

Li Z. ^{[1
]}

He Y. ^{[1
]}

Khodja A.E. ^{[1
]}

机构：

[1] Department of Computer Science, Zhejiang Normal University, Jinhua

[2] Department of Mathematics, Zhejiang Normal University, Jinhua

来源：

Moshi Shibie yu Rengong Zhineng/Pattern Recognition and Artificial Intelligence | 2019年 / 32卷 / 03期

基金：

中国国家自然科学基金;

关键词：

Convolutional Neural Network; Feature Slice Map; Group Convolution; Lightweight Network; Slice Block;

D O I：

10.16451/j.cnki.issn1003-6059.201903005

中图分类号：

学科分类号：

摘要：

The capacities of mobile and embedded devices are quite inadequate for the requirement of the storage capacity and computational resources of convolutional neural network models. Therefore, a lightweight convolutional neural network architecture, network with slice feature map, named SFNet, is proposed. The concept of slice block is introduced. By performing the "slice" processing on the output feature map of the network, each feature map segment is respectively sent to a convolution kernel of different sizes for convolution operation, and then the obtained feature map is concatenated. A simple 1×1 convolution is utilized to fuse the channels of the feature map. The experiments show that compared with the state-of-the-art lightweight convolutional neural networks, SFNet has fewer parameters and floating-point operations, and higher classification accuracy with the same number of convolution kernels and input feature map channels. Compared with the standard convolution, in the case of a significant reduction in network complexity, the classification accuracy is same or higher. © 2019, Science Press. All right reserved.

引用

页码：237 / 246

页数：9

共 46 条

[1]

Krizhevsky A., Sutskever I., Hinton G.E., ImageNet Classification with Deep Convolutional Neural Networks, pp. 1097-1105, (2012)

[2]

Ren S.Q., He K.M., Girshick R., Et al., Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks, IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 6, pp. 1137-1149, (2016)

[3]

Long J., Shelhamer E., Darrell T., Fully Convolutional Networks for Semantic Segmentation, Proc of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431-3440, (2015)

[4]

Simonyan K., Zisserman A., Very Deep Convolutional Networks for Large-Scale Image Recognition

[5]

Deng J., Dong W., Socher R., Et al., ImageNet: A Large-Scale Hie-rarchical Image Database, Proc of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 248-255, (2009)

[6]

Szegedy C., Liu W., Jia Y.Q., Et al., Going Deeper with ConvolutionsProc of the IEEE Conference on Computer Vision and Pattern Recognition, (2015)

[7]

He K.M., Zhang X.Y., Ren S.Q., Et al., Deep Residual Learning for Image Recognition, Proc of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770-778, (2016)

[8]

Huang G., Liu Z., Van Der Laurens M., Et al., Densely Connected Convolutional Networks, Proc of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2261-2269, (2017)

[9]

Howard A.G., Zhu M.L., Chen B., Et al., MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

[10]

Han S., Pool J., Tran J., Et al., Learning Both Weights and Connections for Efficient Neural Network, Advances in Neural Information Processing Systems 28, pp. 1135-1143, (2015)

← 1 2 3 4 5 →