AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

Uncertainty Estimation via Hyperspherical Confidence Mapping

Eunseo Choi, Ho-Yeon Kim, Jaewon Lee, Taeyong jo, Myungjun lee, Heejin Ahn

ICLR 2026 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Priors and functional variational uncertainty · 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 mixup training to HCM (ablation)HCM (ResNet-18) · CIFAR-10 OOD detection, averageAUROC (%): 85.04 -> 89.44Improved
add mixup training to HCM (ablation)HCM (ResNet-18) · CIFAR-10 near-OODAUROC (%): 82.23 -> 87.90Improved
add mixup training to HCM (ablation)HCM (ResNet-18) · CIFAR-10 far-OODAUROC (%): 86.45 -> 90.12Improved
add mixup training to MSP baseline (ablation)MSP · CIFAR-10 OOD detection, averageAUROC (%): -3.61Hurt
add mixup training to Energy baseline (ablation)Energy · CIFAR-10 OOD detection, averageAUROC (%): -15.34Hurt
add mixup training to KNN baseline (ablation)KNN · CIFAR-10 OOD detection, averageAUROC (%): +2.54Improved
use HCM instead of Ensembles/MC Dropout/EDL for uncertaintyNYU-v2 depth with noisy input · NYU-v2 depthPearson / Spearman: Pearson 0.4919 vs 0.2381 (Ensembles); Spearman 0.5425 vs 0.4684Improved
use HCM instead of variance-based baselinesNYU-v2 depth with noisy input · NYU-v2 depthECE_reg and RMSE: ECE_reg 0.2160 vs 0.0609 (EDL); RMSE 0.1485 vs 0.1189 (MC Dropout)Hurt
use HCM instead of Ensemble/EDL/MC DropoutIndustrial wafer regression · Industrial wafer regressionPearson correlation: 0.8435 vs 0.3227 (Ensemble)Improved
use HCM instead of EnsembleIndustrial wafer regression · Industrial wafer regressionRMSE: 4.6783 -> 5.4022Hurt

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