VRL generates interpretable verbalized features from few-shot image pairs and uses them to train classifiers, outperforming prior LLM-based attribute methods on iNaturalist and Kiki-Bouba.
Kiki or bouba? sound symbolism in vision-and-language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Verbalized Representation Learning for Interpretable Few-Shot Generalization
VRL generates interpretable verbalized features from few-shot image pairs and uses them to train classifiers, outperforming prior LLM-based attribute methods on iNaturalist and Kiki-Bouba.