论文标题
用判别图像贴片在初始化时进行一次镜头网络修剪
One-shot Network Pruning at Initialization with Discriminative Image Patches
论文作者
论文摘要
初始化时（OPAI）时的一声网络修剪是降低网络修剪成本的有效方法。最近，人们越来越相信数据在OPAI中是不必要的。但是，我们通过两种代表性的OPAI方法，即剪切和掌握的消融实验获得了相反的结论。具体来说，我们发现信息数据对于增强修剪性能至关重要。在本文中，我们提出了两种新颖的方法，即歧视性的单发网络修剪（DOP）和超级缝制，以通过高级视觉判别图像贴片来修剪网络。我们的贡献如下。 （1）广泛的实验表明OPAI是数据依赖性的。 （2）超级缝合的性能明显优于基准图像网上的原始OPAI方法，尤其是在高度压缩的模型中。
One-shot Network Pruning at Initialization (OPaI) is an effective method to decrease network pruning costs. Recently, there is a growing belief that data is unnecessary in OPaI. However, we obtain an opposite conclusion by ablation experiments in two representative OPaI methods, SNIP and GraSP. Specifically, we find that informative data is crucial to enhancing pruning performance. In this paper, we propose two novel methods, Discriminative One-shot Network Pruning (DOP) and Super Stitching, to prune the network by high-level visual discriminative image patches. Our contributions are as follows. (1) Extensive experiments reveal that OPaI is data-dependent. (2) Super Stitching performs significantly better than the original OPaI method on benchmark ImageNet, especially in a highly compressed model.
