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 1–29 of 29 papers

TitleStatusHype
No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed ClassifierCode1
Masksembles for Uncertainty EstimationCode1
Multi-class probabilistic classification using inductive and cross Venn-Abers predictorsCode1
FedFA: Federated Learning with Feature Anchors to Align Features and Classifiers for Heterogeneous DataCode1
PrePrompt: Predictive prompting for class incremental learningCode1
Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without ForgettingCode1
Multivariate Confidence Calibration for Object DetectionCode1
Danish Fungi 2020 -- Not Just Another Image Recognition DatasetCode1
How Well Do Self-Supervised Models Transfer?Code1
Hidden Heterogeneity: When to Choose Similarity-Based CalibrationCode0
Accuracy-Preserving Calibration via Statistical Modeling on Probability SimplexCode0
Long-tailed Medical Diagnosis with Relation-aware Representation Learning and Iterative Classifier CalibrationCode0
No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID DataCode0
Packed-Ensembles for Efficient Uncertainty EstimationCode0
Improved User Identification through Calibrated Monte-Carlo DropoutCode0
Classifier Calibration: with application to threat scores in cybersecurityCode0
Enhancing Generalized Few-Shot Semantic Segmentation via Effective Knowledge TransferCode0
Expeditious Saliency-guided Mix-up through Random Gradient ThresholdingCode0
Class-wise and reduced calibration methodsCode0
What is Your Metric Telling You? Evaluating Classifier Calibration under Context-Specific Definitions of Reliability—0
Better Classifier Calibration for Small Data Sets—0
Binary Classifier Calibration: Bayesian Non-Parametric Approach—0
Binary Classifier Calibration: Non-parametric approach—0
Binary Classifier Calibration using an Ensemble of Near Isotonic Regression Models—0
Classifier Calibration: A survey on how to assess and improve predicted class probabilities—0
Classifier Calibration with ROC-Regularized Isotonic Regression—0
Decoupling Decision-Making in Fraud Prevention through Classifier Calibration for Business Logic Action—0
FedSA: A Unified Representation Learning via Semantic Anchors for Prototype-based Federated Learning—0
High Frequency Residual Learning for Multi-Scale Image Classification—0
Show:102550

No leaderboard results yet.