Geometric Regularization of Local Activations for Knowledge Transfer in Convolutional Neural Networks

Geometric Regularization of Local Activations for Knowledge Transfer in Convolutional Neural Networks

In this work, we propose a mechanism for knowledge transfer between Convolutional Neural Networks via the geometric regularization of local features produced by the activations of convolutional layers. We formulate appropriate loss functions, driving a “student” model to adapt such that its local fe...

Full description

Bibliographic Details
Main Authors: Ilias Theodorakopoulos, Foteini Fotopoulou, George Economou
Format: Article
Language:English
Published: MDPI AG 2021-08-01
Series:Information
Subjects:
manifold regularization
knowledge transfer
knowledge distillation
deep learning with limited data
Online Access:https://www.mdpi.com/2078-2489/12/8/333

Internet

https://www.mdpi.com/2078-2489/12/8/333

Similar Items