arxivst stuff from arxiv that you should probably bookmark

Towards thinner convolutional neural networks through Gradually Global Pruning

Abstract · Mar 29, 2017 07:31 ·


Arxiv Abstract

  • Zhengtao Wang
  • Ce Zhu
  • Zhiqiang Xia
  • Qi Guo
  • Yipeng Liu

Deep network pruning is an effective method to reduce the storage and computation cost of deep neural networks when applying them to resource-limited devices. Among many pruning granularities, neuron level pruning will remove redundant neurons and filters in the model and result in thinner networks. In this paper, we propose a gradually global pruning scheme for neuron level pruning. In each pruning step, a small percent of neurons were selected and dropped across all layers in the model. We also propose a simple method to eliminate the biases in evaluating the importance of neurons to make the scheme feasible. Compared with layer-wise pruning scheme, our scheme avoid the difficulty in determining the redundancy in each layer and is more effective for deep networks. Our scheme would automatically find a thinner sub-network in original network under a given performance.

Read the paper (pdf) »