SOTAVerified

Classifier calibration

Confidence calibration – the problem of predicting probability estimates representative of the true correctness likelihood – is important for classification models in many applications. The two common calibration metrics are Expected Calibration Error (ECE) and Maximum Calibration Error (MCE).

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 11–20 of 29 papers

TitleStatusHype
FedFA: Federated Learning with Feature Anchors to Align Features and Classifiers for Heterogeneous DataCode1
Packed-Ensembles for Efficient Uncertainty EstimationCode0
Class-wise and reduced calibration methodsCode0
What is Your Metric Telling You? Evaluating Classifier Calibration under Context-Specific Definitions of Reliability—0
Hidden Heterogeneity: When to Choose Similarity-Based CalibrationCode0
Classifier Calibration: A survey on how to assess and improve predicted class probabilities—0
Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without ForgettingCode1
No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID DataCode0
Danish Fungi 2020 -- Not Just Another Image Recognition DatasetCode1
Classifier Calibration: with application to threat scores in cybersecurityCode0
Show:102550
← PrevPage 2 of 3Next →

No leaderboard results yet.