LCBM, a variational concept-based model with per-concept embeddings, outperforms unsupervised concept baselines and nearly matches black-box classifiers on seven image datasets.
Artificial Intelligence314, 103822 (2023)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Towards Better Generalization and Interpretability in Unsupervised Concept-Based Models
LCBM, a variational concept-based model with per-concept embeddings, outperforms unsupervised concept baselines and nearly matches black-box classifiers on seven image datasets.