Parameterized Temperature Scaling for Boosting the Expressive Power in Post-Hoc Uncertainty Calibration
Christian Tomani, Daniel Cremers, Florian Buettner
Topics & Concepts
Parameterized complexityComputer scienceBoosting (machine learning)ScalingCalibrationArtificial neural networkDeep neural networksSource codeExpressive powerCode (set theory)AlgorithmArtificial intelligenceMachine learningTheoretical computer scienceSet (abstract data type)StatisticsMathematicsProgramming languageGeometryAnomaly Detection Techniques and ApplicationsAdversarial Robustness in Machine LearningHuman Pose and Action Recognition