Making deep convolutional neural networks more accurate typically comes at
the cost of increased computational and memory resources. In this paper, we
reduce this cost by exploiting the fact that the importance of features
computed by convolutional layers is highly input-dependent, and propose feature
boosting and suppression (FBS), a new method to predictively amplify salient
convolutional channels and skip unimportant ones at run-time. FBS introduces
small auxiliary connections to existing convolutional layers. In contrast to
channel pruning methods which permanently remove channels, it preserves the
full network structures and accelerates convolution by dynamically skipping
unimportant input and output channels. FBS-augmented networks are trained with
conventional stochastic gradient descent, making it readily available for many
state-of-the-art CNNs. We compare FBS to a range of existing channel pruning
and dynamic execution schemes and demonstrate large improvements on ImageNet
classification. Experiments show that FBS can respectively provide $5\times$
and $2\times$ savings in compute on VGG-16 and ResNet-18, both with less than
$0.6\%$ top-5 accuracy loss.

通过 feature boosting and suppression（FBS）方法预测性增强显著卷积通道及跳过不重要通道，动态运行时省略无关重要的输入或输出通道的卷积神经网络（CNN），并在 ImageNet 分类任务中取得了大幅提升。