arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1812.03608cs.NE
收藏

卷积神经网络压缩冗余核的可靠识别

Reliable Identification of Redundant Kernels for Convolutional Neural Network Compression

Wei Wang, Liqiang Zhu

摘要:

针对深度卷积神经网络(CNN)内存占用量大、推理时间长的问题,提出了一种基于特征映射层Ln-norm的剪枝准则.与现有的主要基于卷积核L1范数的剪枝准则不同,该方法利用非线性激活后输出特征图的Ln范数,其中n是变量,从第一个卷积层的1增加到最后一个卷积层的inf。该方法能够准确识别不重要的卷积核,在模型大小和推理精度之间取得了很好的平衡。在ImageNet上的实验和在铁路监控系统中的成功应用表明,该方法优于现有的基于核范数的方法,并且普遍适用于任何具有卷积运算的深度神经网络。

英文摘要:

To compress deep convolutional neural networks (CNNs) with large memory footprint and long inference time, this paper proposes a novel pruning criterion using layer-wised Ln-norm of feature maps. Different from existing pruning criteria, which are mainly based on L1-norm of convolution kernels, the proposed method utilizes Ln-norm of output feature maps after non-linear activations, where n is a variable, increasing from 1 at the first convolution layer to inf at the last convolution layer. With the ability of accurately identifying unimportant convolution kernels, the proposed method achieves a good balance between model size and inference accuracy. The experiments on ImageNet and the successful application in railway surveillance system show that the proposed method outperforms existing kernel-norm-based methods and is generally applicable to any deep neural network with convolution operations.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑