AI Paper Atlas

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

CB-SLICE: Concept-Based Interpretable Error Slice Discovery

Yael Konforti, Mateo Espinosa Zarlenga, Elaf Almahmoud, Mateja Jamnik

ICML 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Prototype and concept dictionary models · 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
restrict slice formation to error-prone concepts selected by ECTP instead of the full concept set (ablation)CB-SLICE · Waterbirds (CBM Joint)SI, Precision@10, MGFImproved
add concept-label and concept-prediction auxiliary losses to the GMM objective (ablation)CB-SLICE · MNIST-Sum (CBM Joint)SI, Precision@10, MGFImproved
use both auxiliary losses together rather than either alone (ablation)CB-SLICE · MNIST-Sum (CBM Joint)SI, Precision@10, MGFImproved
use GMM slicing instead of a linear layer (ablation)CB-SLICE · MNIST-Sum (CBM Seq and Joint)auxiliary classifier accuracy: up to ~10 pointsImproved
replace ResNet-18 encoder with DenseNet-121 (ablation)CB-SLICE · WaterbirdsPrecision@10: 0.79 vs. 0.78 for CBM + Seq and 0.82 for CBM + JointNo clear effect
use CB-SLICE instead of GEORGE on CBMslice discovery · WaterbirdsPrecision@10: up to ~65% pointsImproved
use CB-SLICE instead of GEORGE on CBM Seqslice discovery · MetaShiftPrecision@10: 0.83 vs 0.82No clear effect
increase number of slices t_g up to about 5-10 (ablation)CB-SLICE · MNIST-SumPrecision@10, MGF, aux accuracy: saturate at t_g ~[5, 10]Improved

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