.png){kind=icon}
.png){kind=icon}
Return
Channel pruning on frequency response
.png){kind=icon}
PRE
AI
DOI：10.1007/s11432-022-3951-y.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Network pruning has a significant role in reducing network parameters and accelerating the inference time of the network. Some existing methods prune the network based on the frequency of the data, and finally obtain a sub-network with high accuracy. However, according to our experimental analysis, different frequencies of information in the data contribute differently to the accuracy of the model, and using this information directly for pruning without making a selection will lead to incorrect results. We believe that pruning should retain the convolutional kernels in the network that process important information, while those kernels that process unimportant information should be removed. In this paper, we first investigate the meaning of each frequency band information in the spectrum and their contribution to the prediction accuracy of the network, and according to these results, we propose a new pruning method based on frequency response (PFR). Our PFR finds and removes the convolutional kernels in the network that specialize in processing unimportant information, resulting in a compact neural network model. PFR obtains significant experimental results on different datasets, for example, a 56.0% raduction of float points operations (FLOPs) on ResNet-50 and only 0.37% of Top-1 accuracy degradation on the ImageNet dataset.
Keywords:
deep learning
model compression
filter pruning
channel pruning
frequency response
Journal
IF:
7.6
Papers:
4.9K
Citations:
8.9K