As the network structure of convolutional neural network (CNN) becomes deeper and wider, network optimization, such as pruning, has received ever-increasing research focus. This paper propose a new pruning strategy based on Feature Extraction Ability Measurement (FEAM), which is a novel index of the feature extraction ability from both theoretical analysis and practical operation. Firstly, FEAM is computed as the product of the the kernel sparsity and feature dispersion. Kernel sparsity describes the ability of feature extraction in theory, and feature dispersion represents the feature extraction ability in practical operation. Secondly, FEAMs of all filters in the network are normalized so that the pruning operation can be applied to cross-layer filters. Finally, filters with weak FEAM are pruned to obtain a compact CNN model. In addition, fine-tuning is adopted to restore the generalization ability. Experiments on CAFAR-10 and CUB-200-2011 demonstrate the effectiveness of our method.

随着卷积神经网络（CNN）的网络结构变得越来越广泛，诸如修剪之类的网络优化受到越来越多的研究关注。本文提出了一种基于特征提取能力度量（FEAM）的修剪策略，从理论分析和实际操作两个方面都提出了一种新的特征提取能力指标。首先，FEAM被计算为内核稀疏度和特征离散度的乘积。核稀疏性从理论上描述了特征提取的能力，特征离散代表了实际操作中的特征提取能力。其次，对网络中所有过滤器的FEAM进行归一化，以便将修剪操作应用于跨层过滤器。最后，修剪具有弱FEAM的滤波器，以获得紧凑的CNN模型。此外，通过微调可以恢复泛化能力。在CAFAR-10和CUB-200-2011上进行的实验证明了我们方法的有效性。