论文标题
渠道修剪以分类损失和特征重要性为指导
Channel Pruning Guided by Classification Loss and Feature Importance
论文作者
论文摘要
在这项工作中，我们提出了一种新的逐层通道修剪方法，称为通道修剪，以分类损失和特征重要性为指导（CPLI）。与仅考虑如何重建下一层功能的现有逐层通道修剪方法相反，我们的方法还将分类损失考虑到通道修剪过程中。我们还观察到，在下一个修剪阶段将删除一些重建的功能。因此，不必重建这些功能。为此，我们提出了一种新策略来抑制不重要的功能的影响（即，将在下一个修剪阶段删除这些功能）。我们在三个基准数据集（即CIFAR-10，ImageNet和UCF-101）上进行的全面实验证明了我们的CPLI方法的有效性。
In this work, we propose a new layer-by-layer channel pruning method called Channel Pruning guided by classification Loss and feature Importance (CPLI). In contrast to the existing layer-by-layer channel pruning approaches that only consider how to reconstruct the features from the next layer, our approach additionally take the classification loss into account in the channel pruning process. We also observe that some reconstructed features will be removed at the next pruning stage. So it is unnecessary to reconstruct these features. To this end, we propose a new strategy to suppress the influence of unimportant features (i.e., the features will be removed at the next pruning stage). Our comprehensive experiments on three benchmark datasets, i.e., CIFAR-10, ImageNet, and UCF-101, demonstrate the effectiveness of our CPLI method.
