AI Paper Atlas

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

Parameterized Temperature Scaling for Boosting the Expressive Power in Post-Hoc Uncertainty Calibration

Christian Tomani, Daniel Cremers, Florian Buettner

ECCV 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Confidence calibration objectives · 45 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 non-linear neural-network temperature instead of linear model (ablation)PTS · ImageNet (5 models)ECE: 1.36 -> 1.28Improved
replace ETS (3 fixed temperatures) with prediction-specific temperatures (PTS)ETS · CIFAR-100 VGG19ECE: 2.11 -> 0.82Improved
replace TS with PTSTS · ImageNet MobileNetV2ECE: 5.91 -> 1.43Improved
PTS versus ETS on simple settingsPTS · CIFAR-10 (ECE_KDE)ECE: 1.82 -> 1.49No clear effect
increase hidden-layer size of the temperature network (ablation)PTS · ImageNet MobileNetV2ECE: additional improvement in ECE of 52%Improved
ensemble of 3 temperatures instead of single temperature (ablation)TS · ImageNet MobileNetV2ECE: improved ECE (50% for MobileNetV2 trained on ImageNet)Improved
reduce validation set to 10% of the standard size (ablation)PTS · ImageNet (5 models, normalized ECE)ECE relative to PTS: ETS 0.40, TS 0.71, IRM 0.83 relative to PTS at 10%Hurt
vary number of ECE bins from 5 to 20 (ablation)PTS · ImageNet (5 models)ECENo clear effect
use non-parametric IROvA instead of TS-based calibrators on small validation sets (ablation)IROvA · ImageNet MobileNetV2ECE: IROvA 6.84 vs PTS 1 at 10% validationHurt

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