Three-Dimensional Convolutional Neural Network Pruning with Regularization-Based Method

Yuxin Zhang, Huan Wang, Yang Luo, Lu Yu, Haoji Hu, Hangguan Shan, Tony Q.S. Quek

研究成果: Conference contribution

3 引文 斯高帕斯(Scopus)

摘要

Despite enjoying extensive applications in video analysis, three-dimensional convolutional neural networks (3D CNNs) are restricted by their massive computation and storage consumption. To solve this problem, we propose a three-dimensional regularization-based neural network pruning method to assign different regularization parameters to different weight groups based on their importance to the network. Further we analyze the redundancy and computation cost for each layer to determine the different pruning ratios. Experiments show that pruning based on our method can lead to 2× theoretical speedup with only 0.41% accuracy loss for 3D-ResNet18 and 3.28% accuracy loss for C3D. The proposed method performs favorably against other popular methods for model compression and acceleration.

原文English
主出版物標題2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings
發行者IEEE Computer Society
頁面4270-4274
頁數5
ISBN(電子)9781538662496
DOIs
出版狀態Published - 2019 九月
事件26th IEEE International Conference on Image Processing, ICIP 2019 - Taipei, Taiwan
持續時間: 2019 九月 222019 九月 25

出版系列

名字Proceedings - International Conference on Image Processing, ICIP
2019-September
ISSN(列印)1522-4880

Conference

Conference26th IEEE International Conference on Image Processing, ICIP 2019
國家/地區Taiwan
城市Taipei
期間19-09-2219-09-25

All Science Journal Classification (ASJC) codes

  • 軟體
  • 電腦視覺和模式識別
  • 訊號處理

指紋

深入研究「Three-Dimensional Convolutional Neural Network Pruning with Regularization-Based Method」主題。共同形成了獨特的指紋。

引用此