A verifiable CBM framework grounds concepts in localized image patches, achieving comparable accuracy to standard CBMs on medical benchmarks while enabling direct inspection of concept correctness.
Advances in Neural Information Processing Systems35, 23386–23397 (2022)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
AC-MIL adds an adversarial residual branch and spatial diversity constraint to multiple instance learning so that volume-level quality labels produce localized, interpretable concept maps while preserving competitive grading accuracy.
citing papers explorer
-
Towards Fine-Grained and Verifiable Concept Bottleneck Models
A verifiable CBM framework grounds concepts in localized image patches, achieving comparable accuracy to standard CBMs on medical benchmarks while enabling direct inspection of concept correctness.
-
AC-MIL: Weakly Supervised Atrial LGE-MRI Quality Assessment via Adversarial Concept Disentanglement
AC-MIL adds an adversarial residual branch and spatial diversity constraint to multiple instance learning so that volume-level quality labels produce localized, interpretable concept maps while preserving competitive grading accuracy.
- CLIF: Concept-Level Influence Functions for Transparent Bottleneck Models