Unsupervised Adversarial Domain Adaptation with Error-Correcting Boundaries and Feature Adaption Metric for Remote-Sensing Scene Classification

Unsupervised Adversarial Domain Adaptation with Error-Correcting Boundaries and Feature Adaption Metric for Remote-Sensing Scene Classification

Unsupervised domain adaptation (UDA) based on adversarial learning for remote-sensing scene classification has become a research hotspot because of the need to alleviating the lack of annotated training data. Existing methods train classifiers according to their ability to distinguish features from...

Full description

Bibliographic Details
Main Authors: Chenhui Ma, Dexuan Sha, Xiaodong Mu
Format: Article
Language:English
Published: MDPI AG 2021-03-01
Series:Remote Sensing
Subjects:
remote-sensing scene classification
adversarial learning
unsupervised domain adaptation
target-domain-specific classifier boundaries
domain invariant features
Online Access:https://www.mdpi.com/2072-4292/13/7/1270

Internet

https://www.mdpi.com/2072-4292/13/7/1270

Similar Items