设计具有柱状阶段的简洁卷积网络
Designing Concise ConvNets with Columnar Stages
AI总结:
本文提出柱状阶段网络CoSNet,通过输入复制、少核并行卷积的柱状堆叠并减少1x1卷积,在资源受限场景下以低参数和低FLOPs实现与知名模型相当的性能。
摘要:
在视觉Transformer时代,VanillaNet近期的成功展示了简单且简洁的卷积神经网络(ConvNets)的巨大潜力。此类模型主要关注运行时性能,但为了进一步增强其实用性,同时关注其他方面(如FLOPs、参数数量等)也至关重要。为此,我们引入了一种令人耳目一新的ConvNet宏观设计,称为柱状阶段网络(CoSNet)。CoSNet具有系统化开发的简单且简洁的结构、更小的深度、较低的参数数量、较低的FLOPs以及无注意力操作,非常适合资源受限的部署。CoSNet的关键创新在于部署由输入复制馈送的、具有更少卷积核的并行卷积,使用这些卷积的柱状堆叠,并尽量减少1x1卷积层的使用。我们的综合评估表明,CoSNet在资源受限场景下可与许多知名ConvNet和Transformer设计相媲美。代码:https://github.com/ashishkumar822/CoSNet
英文摘要:
In the era of vision Transformers, the recent success of VanillaNet shows the huge potential of simple and concise convolutional neural networks (ConvNets). Where such models mainly focus on runtime, it is also crucial to simultaneously focus on other aspects, e.g., FLOPs, parameters, etc, to strengthen their utility further. To this end, we introduce a refreshing ConvNet macro design called Columnar Stage Network (CoSNet). CoSNet has a systematically developed simple and concise structure, smaller depth, low parameter count, low FLOPs, and attention-less operations, well suited for resource-constrained deployment. The key novelty of CoSNet is deploying parallel convolutions with fewer kernels fed by input replication, using columnar stacking of these convolutions, and minimizing the use of 1x1 convolution layers. Our comprehensive evaluations show that CoSNet rivals many renowned ConvNets and Transformer designs under resource-constrained scenarios. Code: https://github.com/ashishkumar822/CoSNet
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。