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
FedSA: A Unified Representation Learning via Semantic Anchors for Prototype-based Federated Learning—0
Enhancing Generalized Few-Shot Semantic Segmentation via Effective Knowledge TransferCode0
Improved User Identification through Calibrated Monte-Carlo DropoutCode0
Accuracy-Preserving Calibration via Statistical Modeling on Probability SimplexCode0
Decoupling Decision-Making in Fraud Prevention through Classifier Calibration for Business Logic Action—0
Classifier Calibration with ROC-Regularized Isotonic Regression—0
Expeditious Saliency-guided Mix-up through Random Gradient ThresholdingCode0
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
Show:102550
← PrevPage 2 of 3Next →

No leaderboard results yet.