Deep Domain Adaptation Based on Adversarial Network With Graph Regularization

Deep Domain Adaptation Based on Adversarial Network With Graph Regularization

Although most transfer learning methods can reduce the difference of the feature distributions between the source and target domains effectively, some classes in the two domains may still be misaligned after domain adaptation, especially for the classes with similar features such as “bicy...

Full description

Bibliographic Details
Main Authors: Xu Jia, Na Ma, Fuming Sun
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Adversarial network
domain adaptation
graph regularization
image classification
transfer learning
Online Access:https://ieeexplore.ieee.org/document/9246535/

Internet

https://ieeexplore.ieee.org/document/9246535/

Similar Items