Knowledge Transfer via Student-Teacher Collaboration

Tianxiao Gao, Ruiqin Xiong, Zhenhua Liu, Siwei ma, Feng Wu, Tiejun Huang, Wen Gao

TL;DR: We propose a novel knowledge transfer method which employs a student-teacher collaboration network.

Abstract: Accompanying with the flourish development in various fields, deep neural networks, however, are still facing with the plight of high computational costs and storage. One way to compress these heavy models is knowledge transfer (KT), in which a light student network is trained through absorbing the knowledge from a powerful teacher network. In this paper, we propose a novel knowledge transfer method which employs a Student-Teacher Collaboration (STC) network during the knowledge transfer process. This is done by connecting the front part of the student network to the back part of the teacher network as the STC network. The back part of the teacher network takes the intermediate representation from the front part of the student network as input to make the prediction. The difference between the prediction from the collaboration network and the output tensor from the teacher network is taken into account of the loss during the train process. Through back propagation, the teacher network provides guidance to the student network in a gradient signal manner. In this way, our method takes advantage of the knowledge from the entire teacher network, who instructs the student network in learning process. Through plentiful experiments, it is proved that our STC method outperforms other KT methods with conventional strategy.

Keywords: Network Compression and Acceleration, Knowledge Transfer, Student-Teacher Collaboration, Deep Learning.