# FALCON: Fast and Lightweight Convolution for Compressing and Accelerating CNN

25 Sep 2019Chun QuanJun-Gi JangHyun Dong LeeU Kang

How can we efficiently compress Convolutional Neural Networks (CNN) while retaining their accuracy on classification tasks? A promising direction is based on depthwise separable convolution which replaces a standard convolution with a depthwise convolution and a pointwise convolution... (read more)

PDF Abstract