The learning capability of a neural network improves with increasing depth at
higher computational costs. Wider layers with dense kernel connectivity
patterns furhter increase this cost and may hinder real-time inference. We
propose feature map and kernel level pruning for reducing the computational
complexity of a deep convolutional neural network. Pruning feature maps reduces
the width of a layer and hence does not need any sparse representation.
Further, kernel pruning converts the dense connectivity pattern into a sparse
one. Due to coarse nature, these pruning granularities can be exploited by GPUs
and VLSI based implementations. We propose a simple and generic strategy to
choose the least adversarial pruning masks for both granularities. The pruned
networks are retrained which compensates the loss in accuracy. We obtain the
best pruning ratios when we prune a network with both granularities.
Experiments with the CIFAR-10 dataset show that more than 85% sparsity can be
induced in the convolution layers with less than 1% increase in the
missclassification rate of the baseline network.

通过对特征图和卷积核级别进行修剪，可以减少深度卷积神经网络的计算复杂性，而且在 CIFAR-10 数据集上的实验证明，在保持基线网络误分类率不到 1% 的情况下，可以在卷积层中引入超过 85% 的稀疏性。