TRUST adapts a vision model to an unlabeled target domain by generating pseudo-labels from captions, weighting them by caption-based uncertainty, and aligning image and text features with a soft contrastive loss, reporting SOTA on DomainNet and GeoNet.
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
UNVERDICTED 1representative citing papers
citing papers explorer
-
TRUST: Leveraging Text Robustness for Unsupervised Domain Adaptation
TRUST adapts a vision model to an unlabeled target domain by generating pseudo-labels from captions, weighting them by caption-based uncertainty, and aligning image and text features with a soft contrastive loss, reporting SOTA on DomainNet and GeoNet.