Timezone: »

Learning Student-Friendly Teacher Networks for Knowledge Distillation
Dae Young Park · Moon-Hyun Cha · changwook jeong · Daesin Kim · Bohyung Han

Wed Dec 08 04:30 PM -- 06:00 PM (PST) @ None #None

We propose a novel knowledge distillation approach to facilitate the transfer of dark knowledge from a teacher to a student. Contrary to most of the existing methods that rely on effective training of student models given pretrained teachers, we aim to learn the teacher models that are friendly to students and, consequently, more appropriate for knowledge transfer. In other words, at the time of optimizing a teacher model, the proposed algorithm learns the student branches jointly to obtain student-friendly representations. Since the main goal of our approach lies in training teacher models and the subsequent knowledge distillation procedure is straightforward, most of the existing knowledge distillation methods can adopt this technique to improve the performance of diverse student models in terms of accuracy and convergence speed. The proposed algorithm demonstrates outstanding accuracy in several well-known knowledge distillation techniques with various combinations of teacher and student models even in the case that their architectures are heterogeneous and there is no prior knowledge about student models at the time of training teacher networks

Author Information

Moon-Hyun Cha (Samsung)
changwook jeong (Samsung)
Daesin Kim
Bohyung Han (Seoul National University)

More from the Same Authors