Decoupled knowledge distillation method based on meta-learning

Decoupled knowledge distillation method based on meta-learning

With the advancement of deep learning techniques, the number of model parameters has been increasing, leading to significant memory consumption and limits in the deployment of such models in real-time applications. To reduce the number of model parameters and enhance the generalization capability of...

Full description

Bibliographic Details
Main Authors: Wenqing Du, Liting Geng, Jianxiong Liu, Zhigang Zhao, Chunxiao Wang, Jidong Huo
Format: Article
Language:English
Published: Elsevier 2024-03-01
Series:High-Confidence Computing
Subjects:
Model compression
Knowledge distillation
Meta-learning
Decoupled loss
Online Access:http://www.sciencedirect.com/science/article/pii/S2667295223000624

Internet

http://www.sciencedirect.com/science/article/pii/S2667295223000624

Similar Items