Z-CBMs achieve zero-shot interpretable predictions by retrieving concepts from a million-vocabulary web bank via cross-modal search and regressing labels with sparse linear regression.
Vlg-cbm: Train- ing concept bottleneck models with vision-language guid- ance
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Zero-shot Concept Bottleneck Models
Z-CBMs achieve zero-shot interpretable predictions by retrieving concepts from a million-vocabulary web bank via cross-modal search and regressing labels with sparse linear regression.
- Beyond Explainable AI (XAI): An Overdue Paradigm Shift and Post-XAI Research Directions