COCA Method for SF-UniDA

Sign In

insight - COCA Method for SF-UniDA

COCA: Classifier-Oriented Calibration for Source-Free Universal Domain Adaptation

COCA introduces a novel approach using textual prototypes to enhance few-shot learners in the SF-UniDA scenario.

COCA: Classifier-Oriented Calibration via Textual Prototype for Source-Free Universal Domain Adaptation

COCA method utilizes textual prototypes for few-shot learners in SF-UniDA, outperforming existing models.

1

About

Products | Resources

Read more

Insights

© 2024 by Linnk AI