Head Network Distillation: Splitting Distilled Deep Neural Networks for Resource-Constrained Edge Computing Systems

Head Network Distillation: Splitting Distilled Deep Neural Networks for Resource-Constrained Edge Computing Systems

As the complexity of Deep Neural Network (DNN) models increases, their deployment on mobile devices becomes increasingly challenging, especially in complex vision tasks such as image classification. Many of recent contributions aim either to produce compact models matching the limited computing capa...

Full description

Bibliographic Details
Main Authors: Yoshitomo Matsubara, Davide Callegaro, Sabur Baidya, Marco Levorato, Sameer Singh
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Deep neural networks
edge computing
head network distillation
knowledge distillation
Online Access:https://ieeexplore.ieee.org/document/9265295/

Internet

https://ieeexplore.ieee.org/document/9265295/

Similar Items