A prior-guided hybrid concept bottleneck model improves concept detection at low annotation rates without losing diagnostic accuracy, as shown on mammographic masses, calcifications, and lung nodules.
In: Proceedings of the 37th International Conference on Machine Learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Less Annotation, More Interpretation: Prior-Guided Concept Bottleneck Models for Interpretable Cancer Imaging Diagnosis
A prior-guided hybrid concept bottleneck model improves concept detection at low annotation rates without losing diagnostic accuracy, as shown on mammographic masses, calcifications, and lung nodules.