A prompt-learning method for UDA that uses source-prompt predictions to build better pseudo-labels and a Wasserstein clustering term to keep target text prompts aligned with visual embeddings.
Domain-agnostic mutual prompting for unsuper- vised domain adaptation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Preserving Clusters in Prompt Learning for Unsupervised Domain Adaptation
A prompt-learning method for UDA that uses source-prompt predictions to build better pseudo-labels and a Wasserstein clustering term to keep target text prompts aligned with visual embeddings.