A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Network Decoupling: From Regular to Depthwise Separable Convolutions
[article]
2018
arXiv
pre-print
Depthwise separable convolution has shown great efficiency in network design, but requires time-consuming training procedure with full training-set available. This paper first analyzes the mathematical relationship between regular convolutions and depthwise separable convolutions, and proves that the former one could be approximated with the latter one in closed form. We show depthwise separable convolutions are principal components of regular convolutions. And then we propose network
arXiv:1808.05517v1
fatcat:hlw5g6ibwbehbodemwojzqkdyq