Unsupervised Domain Adaptation Based on Pseudo-Label Confidence

Unsupervised Domain Adaptation Based on Pseudo-Label Confidence

Unsupervised domain adaptation aims to align the distributions of data in source and target domains, as well as assign the labels to data in the target domain. In this paper, we propose a new method named Unsupervised Domain Adaptation based on Pseudo-Label Confidence (UDA-PLC). Concretely, UDA-PLC...

Full description

Bibliographic Details
Main Authors: Tingting Fu, Ying Li
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
Distribution alignment
label propagation
structured prediction
transfer learning
unsupervised domain adaptation
Online Access:https://ieeexplore.ieee.org/document/9449910/

Internet

https://ieeexplore.ieee.org/document/9449910/

Similar Items