TY - GEN
T1 - Convolutional Layers Acceleration By Exploring Optimal Filter Structures
AU - Chen, Hsi Ling
AU - Yang, Jar Ferr
AU - Mao, Song An
N1 - Funding Information:
This work was partially supported by the Ministry of Science and Technology, Taiwan, under Grant MOST 111-2221-E-080 and Qualcomm, USA under Grant SOW#NAT-487842.
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - CNN models are becoming more and more mature, many of them adopt deeper structures to better accomplish the task objectives, such that the increased computational and storage burdens are unfavorable for the implementation in edge devices. In this paper, we propose an approach to optimize the filter structure by starting from the convolutional filter and finding their minimum structure. The reductions of the filters for the minimum structure in terms of space and channels, the number of model parameters and the computational complexity are effectively reduced. Since the current channel pruning method prunes the same channel for each convolutional layer, which easily leads to a trade-off between the pruning rate and accuracy loss. Instead we propose a new channel pruning approach to find the most suitable required channels for each filter to provide a more detailed pruning method. Experiments conducted on the classification CNN models, such as VGG16 and ResNet56, show that the proposed method can successfully reduce the computations of the models without losing much model accuracy effectively. The proposed method performs well in compressing the model and reducing the number of parameters required by the models for real applications.
AB - CNN models are becoming more and more mature, many of them adopt deeper structures to better accomplish the task objectives, such that the increased computational and storage burdens are unfavorable for the implementation in edge devices. In this paper, we propose an approach to optimize the filter structure by starting from the convolutional filter and finding their minimum structure. The reductions of the filters for the minimum structure in terms of space and channels, the number of model parameters and the computational complexity are effectively reduced. Since the current channel pruning method prunes the same channel for each convolutional layer, which easily leads to a trade-off between the pruning rate and accuracy loss. Instead we propose a new channel pruning approach to find the most suitable required channels for each filter to provide a more detailed pruning method. Experiments conducted on the classification CNN models, such as VGG16 and ResNet56, show that the proposed method can successfully reduce the computations of the models without losing much model accuracy effectively. The proposed method performs well in compressing the model and reducing the number of parameters required by the models for real applications.
UR - http://www.scopus.com/inward/record.url?scp=85146269291&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85146269291&partnerID=8YFLogxK
U2 - 10.1109/RASSE54974.2022.9989667
DO - 10.1109/RASSE54974.2022.9989667
M3 - Conference contribution
AN - SCOPUS:85146269291
T3 - RASSE 2022 - IEEE International Conference on Recent Advances in Systems Science and Engineering, Symposium Proceedings
BT - RASSE 2022 - IEEE International Conference on Recent Advances in Systems Science and Engineering, Symposium Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 IEEE International Conference on Recent Advances in Systems Science and Engineering, RASSE 2022
Y2 - 7 November 2022 through 10 November 2022
ER -