no code implementations • 25 Sep 2019 • Jun-Gi Jang, Chun Quan, Hyun Dong Lee, U Kang
By exploiting the knowledge of a trained standard model and carefully determining the order of depthwise separable convolution via GEP, FALCON achieves sufficient accuracy close to that of the trained standard model.
no code implementations • 25 Sep 2019 • Chun Quan, Jun-Gi Jang, Hyun Dong Lee, U Kang
A promising direction is based on depthwise separable convolution which replaces a standard convolution with a depthwise convolution and a pointwise convolution.