Loss Functions

Learning to Defer to Multiple Experts: Consistent Surrogate Losses, Confidence Calibration, and Conformal Ensembles AISTATS 2023 Learning with Logical Constraints but without Shortcut Satisfaction ICLR 2023 LegendreTron: Uprising Proper Multiclass Loss Learning ICML 2023 Linear-Covariance Loss for End-to-End Learning of 6D Pose Estimation ICCV 2023 Local and Global Logit Adjustments for Long-Tailed Learning ICCV 2023 Local Temperature Beam Search: Avoid Neural Text DeGeneration via Enhanced Calibration ACL 2023 Look-back Decoding for Open-Ended Text Generation EMNLP 2023 Making Pre-trained Language Models both Task-solvers and Self-calibrators ACL 2023 Maximization of Average Precision for Deep Learning with Adversarial Ranking Robustness NeurIPS 2023 Maximum Entropy Loss, the Silver Bullet Targeting Backdoor Attacks in Pre-trained Language Models ACL 2023 Minimum-Risk Recalibration of Classifiers NeurIPS 2023 Mitigating Framing Bias with Polarity Minimization Loss EMNLP 2023 Mitigating Intrinsic Named Entity-Related Hallucinations of Abstractive Text Summarization EMNLP 2023 Mitigating Memorization of Noisy Labels by Clipping the Model Prediction ICML 2023 Mitigating Negative Transfer in Multi-Task Learning with Exponential Moving Average Loss Weighting Strategies (Student Abstract) AAAI 2023 Model Calibration in Dense Classification with Adaptive Label Perturbation ICCV 2023 Model Intrinsic Features of Fine-tuning based Text Summarization Models for Factual Consistency ACL 2023 NCTV: Neural Clamping Toolkit and Visualization for Neural Network Calibration AAAI 2023 NeRF-MS: Neural Radiance Fields with Multi-Sequence ICCV 2023 NewsDialogues: Towards Proactive News Grounded Conversation ACL 2023 On Calibrating Semantic Segmentation Models: Analyses and an Algorithm CVPR 2023 On Classification-Calibration of Gamma-Phi Losses COLT 2023 One-vs-the-Rest Loss to Focus on Important Samples in Adversarial Training ICML 2023 On Regularization and Inference with Label Constraints ICML 2023 On Second-Order Scoring Rules for Epistemic Uncertainty Quantification ICML 2023