arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1906.07488cs.CV
收藏

加速卷积神经网络的一步剪枝-恢复框架

A One-step Pruning-recovery Framework for Acceleration of Convolutional Neural Networks

Beihang University(北京航空航天大学);Griffith University(格里菲斯大学)

Dong Wang, Lei Zhou, Xiao Bai, Jun Zhou

摘要:

卷积神经网络的加速在过去的几年中受到越来越多的关注。在各种加速技术中,滤波器修剪技术具有其固有的优点,可以有效地减少卷积滤波器的数量。然而,大多数过滤器修剪方法采取繁琐和耗时的逐层修剪恢复策略,以避免准确率的显着下降。在本文中,我们提出了一个有效的过滤器修剪框架来解决这个问题。该方法采用一种新的优化目标函数,以一步剪枝-恢复的方式加速网络,与现有的剪枝方法相比,该方法以更小的代价获得了更高的精度。此外,我们的方法允许网络压缩与全球过滤器修剪。给定全局修剪速率,它可以自适应地确定每个单个卷积层的修剪速率,而这些速率通常在以前的方法中被设置为超参数。使用ImageNet在VGG-16和ResNet-50上进行评估,我们的方法优于几种最先进的方法,在相同甚至更少的浮点运算(FLOPs)下精度下降更少。

英文摘要:

Acceleration of convolutional neural network has received increasing attention during the past several years. Among various acceleration techniques, filter pruning has its inherent merit by effectively reducing the number of convolution filters. However, most filter pruning methods resort to tedious and time-consuming layer-by-layer pruning-recovery strategy to avoid a significant drop of accuracy. In this paper, we present an efficient filter pruning framework to solve this problem. Our method accelerates the network in one-step pruning-recovery manner with a novel optimization objective function, which achieves higher accuracy with much less cost compared with existing pruning methods. Furthermore, our method allows network compression with global filter pruning. Given a global pruning rate, it can adaptively determine the pruning rate for each single convolutional layer, while these rates are often set as hyper-parameters in previous approaches. Evaluated on VGG-16 and ResNet-50 using ImageNet, our approach outperforms several state-of-the-art methods with less accuracy drop under the same and even much fewer floating-point operations (FLOPs).

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。

↑