Highlight Every Step: Knowledge Distillation via Collaborative Teaching

• Main Authors: Zhao, Haoran, Sun, Xin, Dong, Junyu, Chen, Changrui, Dong, Zihe
• Format: Journal Article
• Language: English
• Published: 22-07-2019
• Subjects: Computer Science - Computer Vision and Pattern Recognition; Computer Science - Learning
• DOI: 10.48550/arxiv.1907.09643

High storage and computational costs obstruct deep neural networks to be
deployed on resource-constrained devices. Knowledge distillation aims to train
a compact student network by transferring knowledge from a larger pre-trained
teacher model. However, most existing methods on knowledge distillation ignore
the valuable information among training process associated with training
results. In this paper, we provide a new Collaborative Teaching Knowledge
Distillation (CTKD) strategy which employs two special teachers. Specifically,
one teacher trained from scratch (i.e., scratch teacher) assists the student
step by step using its temporary outputs. It forces the student to approach the
optimal path towards the final logits with high accuracy. The other pre-trained
teacher (i.e., expert teacher) guides the student to focus on a critical region
which is more useful for the task. The combination of the knowledge from two
special teachers can significantly improve the performance of the student
network in knowledge distillation. The results of experiments on CIFAR-10,
CIFAR-100, SVHN and Tiny ImageNet datasets verify that the proposed knowledge
distillation method is efficient and achieves state-of-the-art performance.