Shift-based Primitives for Efficient Convolutional Neural Networks

2019 IEEE Winter Conference on Applications of Computer Vision (WACV)(2018)

引用 19|浏览116
暂无评分
摘要
We propose a collection of three shift-based primitives for building efficient compact CNN-based networks. These three primitives (channel shift, address shift, shortcut shift) can reduce the inference time on GPU while maintains the prediction accuracy. These shift-based primitives only moves the pointer but avoids memory copy, thus very fast. For example, the channel shift operation is 12.7x faster compared to channel shuffle in ShuffleNet but achieves the same accuracy. The address shift and channel shift can be merged into the point-wise group convolution and invokes only a single kernel call, taking little time to perform spatial convolution and channel shift. Shortcut shift requires no time to realize residual connection through allocating space in advance. We blend these shift-based primitives with point-wise group convolution and built two inference-efficient CNN architectures named AddressNet and Enhanced AddressNet. Experiments on CIFAR100 and ImageNet datasets show that our models are faster and achieve comparable or better accuracy.
更多
查看译文
关键词
GPU,AddressNet,point-wise group convolution,channel shift operation,shortcut shift,building efficient compact CNN-based networks,efficient convolutional neural networks,shift-based primitives
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要