Knowledge Squeezed Adversarial Network Compression

no code implementations • 10 Apr 2019 • Shu Changyong, Li Peng, Xie Yuan, Qu Yanyun, Dai Longquan, Ma Lizhuang

Deep network compression has been achieved notable progress via knowledge distillation, where a teacher-student learning manner is adopted by using predetermined loss.

Knowledge Distillation Transfer Learning