A CLIP-based method that searches WordNet nouns as target semantic centers in text-embedding space and uses information maximization for alignment achieves state-of-the-art Universal Domain Adaptation on four benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Target Semantics Clustering via Text Representations for Robust Universal Domain Adaptation
A CLIP-based method that searches WordNet nouns as target semantic centers in text-embedding space and uses information maximization for alignment achieves state-of-the-art Universal Domain Adaptation on four benchmarks.