← Keywords

confidence calibration

173 papers

Explore in graph

Co-occurring keywords

large language model (12755) uncertainty quantification (1365) uncertainty estimation (639) out-of-distribution detection (611) confidence estimation (162) neural network (6616) model calibration (225) question answering (2904) expected calibration error (44) calibration error (58)

Papers

Bridging Precision and Confidence: A Train-Time Loss for Calibrating Object Detection CVPR 2023
Realistic Conversational Question Answering with Answer Selection based on Calibrated Confidence and Uncertainty Measurement EACL 2023
AUC-based Selective Classification AISTATS 2023
Calibrating Deep Neural Networks Using Explicit Regularisation and Dynamic Data Pruning WACV 2023
Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-Grained Environments WACV 2023
The Box Size Confidence Bias Harms Your Object Detector WACV 2023
Sample-Dependent Adaptive Temperature Scaling for Improved Calibration AAAI 2023
Calibration of Machine Reading Systems at Scale ACL 2022
Early Stopping Based on Unlabeled Samples in Text Classification ACL 2022
Confidence Calibration for Intent Detection via Hyperspherical Space and Rebalanced Accuracy-Uncertainty Loss AAAI 2022
Uncalibrated Models Can Improve Human-AI Collaboration NIPS 2022
Mitigating Bias in Calibration Error Estimation AISTATS 2022
A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network Calibration CVPR 2022
Revisit Overconfidence for OOD Detection: Reassigned Contrastive Learning with Adaptive Class-dependent Threshold NAACL 2022
Re-Examining Calibration: The Case of Question Answering EMNLP 2022
Two Coupled Rejection Metrics Can Tell Adversarial Examples Apart CVPR 2022
On the Impact of Spurious Correlation for Out-of-Distribution Detection AAAI 2022
Confidence Calibration for Domain Generalization Under Covariate Shift ICCV 2021
Self-Knowledge Distillation With Progressive Refinement of Targets ICCV 2021
Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibration NIPS 2021
SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness NIPS 2021
MSNet: A Multilevel Instance Segmentation Network for Natural Disaster Damage Assessment in Aerial Videos WACV 2021
Improving Classifier Confidence using Lossy Label-Invariant Transformations AISTATS 2021
CODEs: Chamfer Out-of-Distribution Examples Against Overconfidence Issue ICCV 2021
When in Doubt: Improving Classification Performance with Alternating Normalization EMNLP 2021