Convolution neural network with low operation FLOPS and high accuracy for image recognition

被引：0
作者：
Shih-Chang Hsia
Szu-Hong Wang
Chuan-Yu Chang
机构：
[1] National Yunlin University of Science and Technology,
来源：
Journal of Real-Time Image Processing | 2021年 / 18卷
关键词：
Deep learning; Convolution neural network; DenseNet; Deeper layer;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
The convolution neural network makes deeper and wider for better accuracy, but requires higher computations. When the neural network goes deeper, some information loss is more. To improve this drawback, the residual structure was developed to connect the information of the previous layers. This is a good solution to prevent the loss of information, but it requires a huge amount of parameters for deeper layer operations. In this study, the fast computational algorithm is proposed to reduce the parameters and to save the operations with the modification of DenseNet deep layer block. With channel merging procedures, this solution can reduce the dilemma of multiple growth of the parameter quantity for deeper layer. This approach is not only to reduce the parameters and FLOPs, but also to keep high accuracy. Comparisons with the original DenseNet and RetNet-110, the parameters can be efficiency reduced about 30–70%, while the accuracy degrades little. The lightweight network can be implemented on a low-cost embedded system for real-time application.
引用
收藏
页码：1309 / 1319
页数：10
相关论文
共 30 条
[1]  
Wang C(2018)MALOC: a fully pipelined FPGA accelerator for convolutional neural networks with all layers mapped on chip Lei Gong IEEE Trans. Comput. Aided Des. Integr. Circuit Syst. 37 2601-2612
[2]  
Li X(2019)High-performance FPGA-based CNN accelerator with block-floating-point arithmetic IEEE Trans. Very Large Scale Integr. Syst. 27 1874-1885
[3]  
Chen H(2021)Real-time video fire/smoke detection based on CNN in antifire surveillance systems J. Real-Time Image Process. 18 889-900
[4]  
Zhou X(2020)Convolution neural network joint with mixture of extreme learning machines for feature extraction and classification of accident images J. Real-Time Image Process. 17 1051-1066
[5]  
Lian X(2016)Image super-resolution using deep convolutional networks IEEE Trans. Pattern Anal. Mach. Intell. 38 295-307
[6]  
Liu Z(2020)Low-complexity CNN with 1D and 2D filters for super-resolution J. Real-Time Image Proc. 17 2065-2076
[7]  
Song Z(1998)Gradient-based learning applied to document recognition Proc. IEEE 86 2278-2324
[8]  
Dai J(2018)A CNN accelerator on FPGA using depthwise separable convolution IEEE Trans. Circuits Syst. II 65 1415-1419
[9]  
Zhou W(undefined)undefined undefined undefined undefined-undefined
[10]  
Ji X(undefined)undefined undefined undefined undefined-undefined
123