model calibration

Don’t fear the unlabelled: safe semi-supervised learning via debiasing ICLR 2023 Don’t waste a single annotation: improving single-label classifiers through soft labels EMNLP 2023 Dual Focal Loss for Calibration ICML 2023 Efficiently Controlling Multiple Risks with Pareto Testing ICLR 2023 ESD: Expected Squared Difference as a Tuning-Free Trainable Calibration Measure ICLR 2023 Fair-CDA: Continuous and Directional Augmentation for Group Fairness AAAI 2023 Fast and scalable score-based kernel calibration tests UAI 2023 Label Smoothing for Emotion Detection (Student Abstract) AAAI 2023 Learning Sample Difficulty from Pre-trained Models for Reliable Prediction NeurIPS 2023 Local Temperature Beam Search: Avoid Neural Text DeGeneration via Enhanced Calibration ACL 2023 Making Pre-trained Language Models both Task-solvers and Self-calibrators ACL 2023 Model Calibration in Dense Classification with Adaptive Label Perturbation ICCV 2023 On Calibrating Diffusion Probabilistic Models NeurIPS 2023 On Calibrating Semantic Segmentation Models: Analyses and an Algorithm CVPR 2023 Proximity-Informed Calibration for Deep Neural Networks NeurIPS 2023 Rethinking Data Distillation: Do Not Overlook Calibration ICCV 2023 Revisiting Pathologies of Neural Models under Input Reduction ACL 2023 RoAST: Robustifying Language Models via Adversarial Perturbation with Selective Training EMNLP 2023 Robust distillation for worst-class performance: on the interplay between teacher and student objectives UAI 2023 Scaling of Class-wise Training Losses for Post-hoc Calibration ICML 2023 SELFOOD: Self-Supervised Out-Of-Distribution Detection via Learning to Rank EMNLP 2023 Soft Augmentation for Image Classification CVPR 2023 T-Cal: An Optimal Test for the Calibration of Predictive Models JMLR 2023 Test-time Augmentation for Factual Probing EMNLP 2023 The Fine Print on Tempered Posteriors ACML 2023