Reliable Identification of Redundant Kernels for Convolutional Neural Network Compression
Abstract
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.
- Publication:
-
arXiv e-prints
- Pub Date:
- December 2018
- DOI:
- 10.48550/arXiv.1812.03608
- arXiv:
- arXiv:1812.03608
- Bibcode:
- 2018arXiv181203608W
- Keywords:
-
- Computer Science - Neural and Evolutionary Computing