Image 1 (IMAGE)

Singapore University of Technology and Design

Image 1

Caption

Overview of the proposed Dual-supervised Asymmetric Co-training (DAC) framework for the cross-domain semi-supervised domain generalization (CD-SSDG) task. This task is closely related to Domain Generalization (DG) and Semi-supervised Domain Generalization (SSDG), but presents unique challenges that cannot be addressed by DG or SSDG alone — namely, partially labeled training data and domain shifts between labeled and unlabeled training data.

Credit

SUTD

Usage Restrictions

Image should be used with appropriate caption and credit.

License

Original content

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.