Unsupervised Deep Domain Adaptation Based on Weighted Adversarial Network

Unsupervised Deep Domain Adaptation Based on Weighted Adversarial Network

Recent studies indicate that adversarial learning can reduce distribution discrepancy between domains effectively, but when the samples belonged to different classes have similar characteristics in the domains, they may be incorrectly aligned to similar classes after domain adaption, which gives ris...

Full description

Bibliographic Details
Main Authors: Xu Jia, Fuming Sun
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Adversarial network
domain adaptation
image classification
transfer learning
unsupervised learning
Online Access:https://ieeexplore.ieee.org/document/9052736/

Internet

https://ieeexplore.ieee.org/document/9052736/

Similar Items