arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.01847cs.CV
收藏

通过资源重新分配的网络修剪

Network Pruning via Resource Reallocation

The Chinese University of Hong Kong(香港中文大学);SenseTime Group Limited(商汤集团有限公司);Nanyang Technological University(南洋理工大学)

Yuenan Hou, Zheng Ma, Chunxiao Liu, Zhe Wang, Chen Change Loy

摘要:

通道修剪是一种有效的方法,可以从复杂的网络中删除不重要的通道,从而得到一个小型的紧凑模型。现代方法通常从原始过参数化模型执行迭代修剪过程,这既繁琐又昂贵,特别是当修剪是积极的时。在本文中,我们提出了一个简单而有效的通道修剪技术,称为网络修剪通过rEsource rEalLocation(PEEL),以快速产生所需的超薄模型,成本可以忽略不计。具体而言,PEEL首先构建一个预定义的骨干,然后在其上进行资源重新分配,以在一轮中将参数从信息量较少的层转移到更重要的层,从而放大这些信息层的积极作用。为了证明PEEL的有效性,我们使用ResNet-18、ResNet-50、MobileNetV 2、MobileNetV 3-small和EfficientNet-B 0在ImageNet上进行了大量实验。实验结果表明,在不同的剪枝设置下,PEEL发现的结构表现出与最先进的剪枝算法竞争的性能。我们的代码可在https://github.com/cardwing/Codes-for-PEEL上获得。

英文摘要:

Channel pruning is broadly recognized as an effective approach to obtain a small compact model through eliminating unimportant channels from a large cumbersome network. Contemporary methods typically perform iterative pruning procedure from the original over-parameterized model, which is both tedious and expensive especially when the pruning is aggressive. In this paper, we propose a simple yet effective channel pruning technique, termed network Pruning via rEsource rEalLocation (PEEL), to quickly produce a desired slim model with negligible cost. Specifically, PEEL first constructs a predefined backbone and then conducts resource reallocation on it to shift parameters from less informative layers to more important layers in one round, thus amplifying the positive effect of these informative layers. To demonstrate the effectiveness of PEEL , we perform extensive experiments on ImageNet with ResNet-18, ResNet-50, MobileNetV2, MobileNetV3-small and EfficientNet-B0. Experimental results show that structures uncovered by PEEL exhibit competitive performance with state-of-the-art pruning algorithms under various pruning settings. Our code is available at https://github.com/cardwing/Codes-for-PEEL.

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。

↑