论文标题
组稀疏性：网络压缩的滤波器修剪和分解之间的铰链
Group Sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compression
论文作者
论文摘要
在本文中，我们分析了两种流行的网络压缩技术，即从统一的意义上分析过滤器修剪和低排放分解。通过简单地更改稀疏性正则实施方式，可以相应地得出过滤器修剪和低秩分解。这为网络压缩提供了另一个灵活的选择，因为这些技术相互补充。例如，在具有快捷方式连接的流行网络体系结构中（例如，重新连接），过滤器修剪无法处理重新分解中的最后一个卷积层，而低级别的分解方法可以处理。此外，我们建议以层次的方式共同压缩整个网络。我们的方法证明了它的潜力，因为它与几个基准的最先进的比较相比。
In this paper, we analyze two popular network compression techniques, i.e. filter pruning and low-rank decomposition, in a unified sense. By simply changing the way the sparsity regularization is enforced, filter pruning and low-rank decomposition can be derived accordingly. This provides another flexible choice for network compression because the techniques complement each other. For example, in popular network architectures with shortcut connections (e.g. ResNet), filter pruning cannot deal with the last convolutional layer in a ResBlock while the low-rank decomposition methods can. In addition, we propose to compress the whole network jointly instead of in a layer-wise manner. Our approach proves its potential as it compares favorably to the state-of-the-art on several benchmarks.
