ORC: Network Group-based Knowledge Distillation using Online Role Change

TL;DR

This paper introduces ORC, a network group-based knowledge distillation method that dynamically switches networks between teacher and student roles to improve learning effectiveness, validated on multiple datasets and architectures.

Contribution

It proposes an online role change strategy for network groups, enhancing knowledge transfer by selecting and promoting networks between teacher and student roles during training.

Findings

Achieves superior performance on CIFAR-10, CIFAR-100, and ImageNet.

Demonstrates effectiveness across various backbone architectures.

Improves knowledge distillation by dynamic role assignment.

Abstract

In knowledge distillation, since a single, omnipotent teacher network cannot solve all problems, multiple teacher-based knowledge distillations have been studied recently. However, sometimes their improvements are not as good as expected because some immature teachers may transfer the false knowledge to the student. In this paper, to overcome this limitation and take the efficacy of the multiple networks, we divide the multiple networks into teacher and student groups, respectively. That is, the student group is a set of immature networks that require learning the teacher's knowledge, while the teacher group consists of the selected networks that are capable of teaching successfully. We propose our online role change strategy where the top-ranked networks in the student group are able to promote to the teacher group at every iteration. After training the teacher group using the error samples of the student group to refine the teacher group's knowledge, we transfer the collaborative knowledge from the teacher group to the student group successfully. We verify the superiority of the proposed method on CIFAR-10, CIFAR-100, and ImageNet which achieves high performance. We further show the generality of our method with various backbone architectures such as ResNet, WRN, VGG, Mobilenet, and Shufflenet.