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

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

24 February 2021

Christian Tomani

Florian Buettner

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

10 / 10 papers shown

Title
Optical aberrations in autonomous driving: Physics-informed parameterized temperature scaling for neural network uncertainty calibration D. Wolf Alexander Braun Markus Ulrich 89 0 0 18 Dec 2024
Decoupling of neural network calibration measures D. Wolf Prasannavenkatesh Balaji Alexander Braun Markus Ulrich UQCV 44 3 0 04 Jun 2024
Optimizing Calibration by Gaining Aware of Prediction Correctness Yuchi Liu Lei Wang Yuli Zou James Zou Liang Zheng UQCV 44 1 0 19 Apr 2024
Accuracy-Preserving Calibration via Statistical Modeling on Probability Simplex Yasushi Esaki Akihiro Nakamura Keisuke Kawano Ryoko Tokuhisa Takuro Kutsuna 46 0 0 21 Feb 2024
IW-GAE: Importance Weighted Group Accuracy Estimation for Improved Calibration and Model Selection in Unsupervised Domain Adaptation Taejong Joo Diego Klabjan 43 1 0 16 Oct 2023
Scaling of Class-wise Training Losses for Post-hoc Calibration Seungjin Jung Seung-Woo Seo Yonghyun Jeong Jongwon Choi 37 3 0 19 Jun 2023
Beyond In-Domain Scenarios: Robust Density-Aware Calibration Christian Tomani Futa Waseda Yuesong Shen Daniel Cremers UQCV 34 4 0 10 Feb 2023
Uncertainty Estimation based on Geometric Separation Gabriella Chouraqui L. Cohen Gil Einziger Liel Leman 33 0 0 11 Jan 2023
Adaptive Temperature Scaling for Robust Calibration of Deep Neural Networks Sérgio A. Balanya Juan Maroñas Daniel Ramos OOD 35 13 0 31 Jul 2022
Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles Balaji Lakshminarayanan Alexander Pritzel Charles Blundell UQCV BDL 276 5,675 0 05 Dec 2016