Improving Knowledge Distillation via Transferring Learning Ability

Code

• github.com/brilliantcheng/slkd
  OfficialIn paperpytorch★ 0

Abstract

Existing knowledge distillation methods generally use a teacher-student approach, where the student network solely learns from a well-trained teacher. However, this approach overlooks the inherent differences in learning abilities between the teacher and student networks, thus causing the capacity-gap problem. To address this limitation, we propose a novel method called SLKD.

Tasks

Reproductions