Knowledge distillation in deep learning and its applications

Deep learning based models are relatively large, and it is hard to deploy such models on resource-limited devices such as mobile phones and embedded devices. One possible solution is knowledge distillation whereby a smaller model (student model) is trained by utilizing the information from a larger model (teacher model). In this paper, we present an outlook of knowledge distillation techniques applied to deep learning models. To compare the performances of different techniques, we propose a new metric called distillation metric which compares different knowledge distillation solutions based on models' sizes and accuracy scores. Based on the survey, some interesting conclusions are drawn and presented in this paper including the current challenges and possible research directions.

Automated summary

This paper presents an outlook on knowledge distillation techniques applied to deep learning models, introducing a new metric called distillation metric for comparing performances of different solutions. Interesting conclusions drawn from the survey, along with current challenges and possible research directions, are discussed in the paper.