Knowledge Distillation: A Survey

doi:10.1007/s11263-021-01453-z

Knowledge Distillation: A Survey

2021-03-22

1.5K

PRE

AI

DOI：10.1007/s11263-021-01453-z

Original

Original request for help

Save

Abstract

En 中文

In recent years, deep neural networks have been successful in both industry and academia, especially for computer vision tasks. The great success of deep learning is mainly due to its scalability to encode large-scale data and to maneuver billions of model parameters. However, it is a challenge to deploy these cumbersome deep models on devices with limited resources, e.g., mobile phones and embedded devices, not only because of the high computational complexity but also the large storage requirements. To this end, a variety of model compression and acceleration techniques have been developed. As a representative type of model compression and acceleration, knowledge distillation effectively learns a small student model from a large teacher model. It has received rapid increasing attention from the community. This paper provides a comprehensive survey of knowledge distillation from the perspectives of knowledge categories, training schemes, teacher-student architecture, distillation algorithms, performance comparison and applications. Furthermore, challenges in knowledge distillation are briefly reviewed and comments on future research are discussed and forwarded.

Keywords:

Deep neural networks

Model compression

Knowledge distillation

Knowledge transfer

Teacher– student architecture

Knowledge Distillation: A Survey

Abstract

AI Summary

Journal

Organization