AI Paper Atlas

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

CONSIGN: Conformal Segmentation Informed by Spatial Groupings via Decomposition

Bruno Viti, Elias Karabelas, Martin Holler

ICLR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Confidence calibration objectives · 2 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
use spatially-aware PCA prediction sets instead of pixel-wise RAPS setsCONSIGN · M&Ms-2, MS-CMR19, LIDC, COCOChao estimator (set volume)Improved
use CONSIGN instead of RAPS and SACP on LIDCCONSIGN · LIDCChao estimatorImproved
use CONSIGN instead of RAPS and SACPCONSIGN · COCO-vehiclessample-based estimated coverageImproved
increase principal components from K=2 to K=5 (ablation)CONSIGN · COCOChao estimatorHurt
use probabilistic U-Net samples instead of dropout samplesCONSIGN · LIDC vs cardiac datasetsChao estimatorImproved
use SACP neighborhood aggregation instead of pixel-wiseRAPS · segmentation datasetsvolume, sEC, correlationNo clear effect
use CONSIGN instead of pixel-wise samplingCONSIGN · segmentation datasetsaverage Pearson correlationImproved
use CONSIGN calibration instead of RAPSCONSIGN · all datasetsoffline calibration time (min): ~0.1-1 -> ~5-15Hurt

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