AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Hierarchical Concept-based Interpretable Models

Oscar Hill, Mateo Espinosa Zarlenga, Mateja Jamnik

ICLR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Self-explaining and visual explanation networks · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Concept Splitting sub-concept labels to HiCEM training (ablation)HiCEM · PseudoKitchensdiscovered sub-concept ROC-AUC: 0.75 -> 0.88Improved
add Concept Splitting sub-concept labels to HiCEM training (ablation)HiCEM · AwA2discovered sub-concept ROC-AUC: 0.73 -> 0.88Improved
add Concept Splitting sub-concept labels to HiCEM training (ablation)HiCEM · CUBdiscovered sub-concept ROC-AUC: 0.81 -> 0.85Improved
replace CEM with HiCEM after Concept SplittingCEM · CUBtask accuracy: 0.79 -> 0.74Hurt
replace CEM with HiCEM after Concept SplittingCEM · MNIST-ADD, AwA2, PseudoKitchenstask accuracy: 0.93 -> 0.92 (MNIST-ADD); 0.98 -> 0.98 (AwA2); 0.66 -> 0.65 (PseudoKitchens)No clear effect
use Concept Splitting sub-concepts as supervisionHiCEM · ImageNet user study% yes sub-concept related to parent: 4.0% -> 67.9%Improved
use Concept Splitting image labelsHiCEM · ImageNet user study% yes image consistent with name: 0.9% -> 54.8%Improved
intervene on discovered sub-concepts in HiCEM instead of CEM with discovered conceptsHiCEM · CUB, PseudoKitchenstask accuracy after interventionsMixed
add concept splitting supervision to HiCEM before interventions (ablation)HiCEM · interventionstask accuracyImproved
SAE vs clustering for Concept Splitting (ablation)HiCEM · discovered sub-concept ROC-AUCROC-AUC: CUB 0.90 (clustering) vs 0.85 (SAE); AwA2 0.81 vs 0.88Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy