.png){kind=icon}
返回
SeNPIS: Sequential Network Pruning by class-wise Importance Score
.png){kind=icon}
PRE
AI
DOI：10.1016/j.asoc.2022.109558.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In the last decade, pattern recognition and decision making from images has mainly focused on the development of deep learning architectures, with different types of networks such as sequential, residual and parallel. Although the depth and size varies between models, they all have in common that they can contain multiple filters or neurons that are not important for the purpose of prediction, and that do negatively impact the size of the model and their inference times. Therefore, it is advantageous to use pruning methods that, while largely maintaining the initial performance of the classifier, significantly reduce its size and FLOPs. In parameter reduction, the decision rule is generally based on mathematical criteria, e.g. the amplitude of the weights, but not on the actual impact of the filter or neuron on the classifier performance for each of the classes. Therefore, we propose SeNPIS as a method that involves both filter and neuron selection based on a class-wise importance score, and network resizing to increase parameter reduction and FLOPs in sequential CNN networks. Several tests were performed to compare SeNPIS with other representative state-of-the-art methods, for the CIFAR-10 and Scene-15 datasets. It was found that for similar values of accuracy, and even in some cases with a slight increase in accuracy, SeNPIS significantly reduces the number of parameters by up to an additional 23.5% (i.e., a 51.05% reduction with SeNPIS versus a 27.53% reduction with Gradient) and FLOPs by up to an additional 26.6% (i.e., a 74.82% reduction with SeNPIS versus a 48.16% reduction with Weight) compared to the Weight, Taylor, Gradient and LRP methods.(c) 2022 Elsevier B.V. All rights reserved.
Keyword:
Deep learning
Model compression
Pruning algorithm
Importance score
Convolutional neural network
期刊
IF:
6.6
论文数:
1.4W
被引数:
4.8W
机构
暂无机构信息
引用论文
分享收藏Pruning and quantization for deep neural network acceleration: A survey用于深度神经网络加速的修剪和量化: 一项调查.png)
NEUROCOMPUTING
OAAI
NEUROCOMPUTINGIF6.5
OAAI分享收藏Pruning by explaining: A novel criterion for deep neural network pruning解释修剪: 一种新的深度神经网络修剪准则PATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏
查看更多内容