Transferable adversarial masked self-distillation for unsupervised domain adaptation

Transferable adversarial masked self-distillation for unsupervised domain adaptation

Abstract Unsupervised domain adaptation (UDA) aims to transfer knowledge from a labeled source domain to a related unlabeled target domain. Most existing works focus on minimizing the domain discrepancy to learn global domain-invariant representation using CNN-based architecture while ignoring both...

Full description

Bibliographic Details
Main Authors: Yuelong Xia, Li-Jun Yun, Chengfu Yang
Format: Article
Language:English
Published: Springer 2023-05-01
Series:Complex & Intelligent Systems
Subjects:
Unsupervised domain adaptation
Masked self-distillation
Masked image modeling
Adversarial weighted cross-domain adaptation
Online Access:https://doi.org/10.1007/s40747-023-01094-4

Internet

https://doi.org/10.1007/s40747-023-01094-4

Similar Items