← Optimization & Theory
Machine Learning › Optimization & Theory ›

Loss Functions

1162 directly classified papers

Papers per year

Papers

Unimodal-Concentrated Loss: Fully Adaptive Label Distribution Learning for Ordinal Regression CVPR 2022
AutoLoss-GMS: Searching Generalized Margin-Based Softmax Loss Function for Person Re-Identification CVPR 2022
Calibrating Deep Neural Networks by Pairwise Constraints CVPR 2022
AutoLoss-Zero: Searching Loss Functions From Scratch for Generic Tasks CVPR 2022
AdaFace: Quality Adaptive Margin for Face Recognition CVPR 2022
Enhancing Classifier Conservativeness and Robustness by Polynomiality CVPR 2022
Knowledge Distillation via the Target-Aware Transformer CVPR 2022
A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network Calibration CVPR 2022
SwapMix: Diagnosing and Regularizing the Over-Reliance on Visual Context in Visual Question Answering CVPR 2022
The Devil Is in the Margin: Margin-Based Label Smoothing for Network Calibration CVPR 2022
RecDis-SNN: Rectifying Membrane Potential Distribution for Directly Training Spiking Neural Networks CVPR 2022
Calibrating Imbalanced Classifiers with Focal Loss: An Empirical Study EMNLP 2022
Improving abstractive summarization with energy-based re-ranking EMNLP 2022
YNU-HPCC at SemEval-2022 Task 6: Transformer-based Model for Intended Sarcasm Detection in English and Arabic SEMEVAL 2022
Disentangling Confidence Score Distribution for Out-of-Domain Intent Detection with Energy-Based Learning EMNLP 2022
On the Consistency of Max-Margin Losses AISTATS 2022
CADET: Calibrated Anomaly Detection for Mitigating Hardness Bias IJCAI 2022
Adaptive Label Smoothing with Self-Knowledge in Natural Language Generation EMNLP 2022
Are All Losses Created Equal: A Neural Collapse Perspective NIPS 2022
Learning to Detect Noisy Labels Using Model-Based Features EMNLP 2022
SubER - A Metric for Automatic Evaluation of Subtitle Quality ACL 2022
Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge Distillation ACL 2022
Rethinking the Optimization of Average Precision: Only Penalizing Negative Instances before Positive Ones Is Enough AAAI 2022
What to Learn, and How: Toward Effective Learning from Rationales ACL 2022
Revisiting Over-Smoothness in Text to Speech ACL 2022