Knowledge Squeezed Adversarial Network Compression

Changyong Shu
Changyong Shu
Peng Li
Peng Li
Longquan Dai
Longquan Dai

arXiv: Learning, 2019.

Cited by: 0|Bibtex|Views59|Links
EI

Abstract:

Deep network compression has been achieved notable progress via knowledge distillation, where a teacher-student learning manner is adopted by using predetermined loss. Recently, more focuses have been transferred to employ the adversarial training to minimize the discrepancy between distributions of output from two networks. However, they...More

Code:

Data:

Your rating :
0

 

Tags
Comments