Papers with Code 아카이브
Classifier calibration
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 1
- 보존된 평가 기록
- 1
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).
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Long-tailed Medical Diagnosis with Relation-aware Representation Learning and Iterative Classifier Calibration
FedSA: A Unified Representation Learning via Semantic Anchors for Prototype-based Federated Learning
Enhancing Generalized Few-Shot Semantic Segmentation via Effective Knowledge Transfer
Accuracy-Preserving Calibration via Statistical Modeling on Probability Simplex
Decoupling Decision-Making in Fraud Prevention through Classifier Calibration for Business Logic Action
Classifier Calibration with ROC-Regularized Isotonic Regression
No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier
Expeditious Saliency-guided Mix-up through Random Gradient Thresholding
FedFA: Federated Learning with Feature Anchors to Align Features and Classifiers for Heterogeneous Data
Packed-Ensembles for Efficient Uncertainty Estimation
Class-wise and reduced calibration methods
What is Your Metric Telling You? Evaluating Classifier Calibration under Context-Specific Definitions of Reliability
Hidden Heterogeneity: When to Choose Similarity-Based Calibration
Classifier Calibration: A survey on how to assess and improve predicted class probabilities
Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgetting
No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data
Danish Fungi 2020 -- Not Just Another Image Recognition Dataset
Classifier Calibration: with application to threat scores in cybersecurity
Masksembles for Uncertainty Estimation
How Well Do Self-Supervised Models Transfer?
Multivariate Confidence Calibration for Object Detection
Better Classifier Calibration for Small Data Sets
High Frequency Residual Learning for Multi-Scale Image Classification
Binary Classifier Calibration using an Ensemble of Near Isotonic Regression Models
Binary Classifier Calibration: Non-parametric approach
Binary Classifier Calibration: Bayesian Non-Parametric Approach
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.