An unsupervised adaptation framework for VLMs enables label-free multi-label image recognition by using multi-sampling to counter iconic bias and blend adaptation to match multi-label distributions, outperforming prior unsupervised methods on four datasets.
Open-Vocabulary Multi-Label Classification via Multi-Modal Knowledge Transfer , volume =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Adapting Vision-Language Models from Iconic to Inclusive for Multi-Label Recognition Without Labels
An unsupervised adaptation framework for VLMs enables label-free multi-label image recognition by using multi-sampling to counter iconic bias and blend adaptation to match multi-label distributions, outperforming prior unsupervised methods on four datasets.