arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2211.02206cs.CV
收藏

用于代价受限信道修剪的软掩蔽

Soft Masking for Cost-Constrained Channel Pruning

Stanford University(斯坦福大学);NVIDIA(英伟达)

Ryan Humble, Maying Shen, Jorge Albericio Latorre, Eric Darve1, Jose M. Alvarez

摘要:

结构化通道修剪已被证明可以显著加快现代硬件上卷积神经网络(CNN)的推理时间,而网络准确性损失相对较小。最近的工作是在训练过程中永久地将这些通道归零,我们观察到这会严重影响最终的准确性,特别是当网络被修剪的比例增加时。我们提出了软屏蔽成本约束的信道修剪(SMCP),允许修剪的信道自适应地返回到网络,同时修剪对目标成本约束。通过从移除输入通道的角度添加权重的软掩码重新参数化和通道修剪,我们允许对先前修剪的通道进行梯度更新,并允许通道稍后返回到网络。然后,我们制定输入通道修剪作为一个全球性的资源分配问题。我们的方法在ImageNet分类和PASCAL VOC检测数据集上的性能优于之前的工作。

英文摘要:

Structured channel pruning has been shown to significantly accelerate inference time for convolution neural networks (CNNs) on modern hardware, with a relatively minor loss of network accuracy. Recent works permanently zero these channels during training, which we observe to significantly hamper final accuracy, particularly as the fraction of the network being pruned increases. We propose Soft Masking for cost-constrained Channel Pruning (SMCP) to allow pruned channels to adaptively return to the network while simultaneously pruning towards a target cost constraint. By adding a soft mask re-parameterization of the weights and channel pruning from the perspective of removing input channels, we allow gradient updates to previously pruned channels and the opportunity for the channels to later return to the network. We then formulate input channel pruning as a global resource allocation problem. Our method outperforms prior works on both the ImageNet classification and PASCAL VOC detection datasets.

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。

↑