AI Paper Atlas

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

Extending Temperature Scaling with Homogenizing Maps

Christopher Qian, Feng Liang, Jason Adams

JMLR 2025 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Priors and functional variational uncertainty

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
replace temperature scaling with softplus maps (SP-TS, SP-1, SP-U)temperature scaling · CIFAR-100, five CNNsECE (10 bins)Improved
enforce homogenization (slope constraint) on the softplus map (ablation)SP-U · CIFAR-100 OOD detection (SVHN, LSUN)AUCImproved
use SP-TS (more homogenizing than TS) instead of TStemperature scaling · CIFAR-100 OOD detection (SVHN, LSUN)AUCNo clear effect
use SP-TS instead of SP-1 (greater homogenization) (ablation)SP-1 · CIFAR-100 OOD detectionAUC: 1.122 -> 0.682Improved
add free shift parameter u (SP-U) to softplus mapSP-1 · CIFAR-100 ECEECE (10 bins)No clear effect
add learned logit shift w^T z to SP-U (ablation)SP-U · CIFAR-100 SVHNavg % entropy decrease: 0.597 -> 0.651Hurt
add learned logit shift w^T z (ablation)SP-TS, SP-1, SP-U · CIFAR-100ECE (10 bins)Improved
add learned logit shift w^T z (ablation)SP-U · CIFAR-100 OOD detectionAUCHurt
use SP-TS instead of TStemperature scaling · CIFAR-100underconfidenceHurt
aggregate 200 dropout predictions (Bayesian setting) instead of point predictionrecalibrated CNNs · CIFAR-100calibration and OOD AUCImproved
use SP-TS instead of TS in the Bayesian settingtemperature scaling · CIFAR-100 dropout classifiersECE (10 bins)Improved
use Approach 3 instead of Approach 1 for SP-TSSP-TS · CIFAR-100 BayesianAUCImproved

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