papers AI Learner
The Github is limit! Click to go to the new site.

Single-shot Channel Pruning Based on Alternating Direction Method of Multipliers

2019-02-18
Chengcheng Li, Zi Wang, Xiangyang Wang, Hairong Qi

Abstract

Channel pruning has been identified as an effective approach to constructing efficient network structures. Its typical pipeline requires iterative pruning and fine-tuning. In this work, we propose a novel single-shot channel pruning approach based on alternating direction methods of multipliers (ADMM), which can eliminate the need for complex iterative pruning and fine-tuning procedure and achieve a target compression ratio with only one run of pruning and fine-tuning. To the best of our knowledge, this is the first study of single-shot channel pruning. The proposed method introduces filter-level sparsity during training and can achieve competitive performance with a simple heuristic pruning criterion (L1-norm). Extensive evaluations have been conducted with various widely-used benchmark architectures and image datasets for object classification purpose. The experimental results on classification accuracy show that the proposed method can outperform state-of-the-art network pruning works under various scenarios.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1902.06382

PDF

http://arxiv.org/pdf/1902.06382


Similar Posts

Comments