← Optimization & Theory
Machine Learning › Optimization & Theory ›

Loss Functions

1162 directly classified papers

Papers per year

Papers

Enhancing Classifier Conservativeness and Robustness by Polynomiality CVPR 2022
AutoLoss-GMS: Searching Generalized Margin-Based Softmax Loss Function for Person Re-Identification CVPR 2022
Optimization of Deep Neural Network (DNN) Speech Coder Using a Multi Time Scale Perceptual Loss Function INTERSPEECH 2022
Unimodal-Concentrated Loss: Fully Adaptive Label Distribution Learning for Ordinal Regression CVPR 2022
Calibrating Deep Neural Networks by Pairwise Constraints CVPR 2022
Nearly Optimal Catoni’s M-estimator for Infinite Variance ICML 2022
Air tissue boundary segmentation using regional loss in real-time Magnetic Resonance Imaging video for speech production INTERSPEECH 2022
Polygon-to-Polygon Distance Loss for Rotated Object Detection AAAI 2022
On the Surrogate Gap between Contrastive and Supervised Losses ICML 2022
Regularizing Transformer-based Acoustic Models by Penalizing Attention Weights INTERSPEECH 2022
AdaFocal: Calibration-aware Adaptive Focal Loss NIPS 2022
Exploring Multi-task Learning Based Gender Recognition and Age Estimation for Class-imbalanced Data INTERSPEECH 2022
Learning sparse representations of preferences within Choquet expected utility theory UAI 2022
Audio Anti-spoofing Using Simple Attention Module and Joint Optimization Based on Additive Angular Margin Loss and Meta-learning INTERSPEECH 2022
Loss as the Inconsistency of a Probabilistic Dependency Graph: Choose Your Model, Not Your Loss Function AISTATS 2022
Improving Speech Enhancement through Fine-Grained Speech Characteristics INTERSPEECH 2022
Knowledge Distillation via the Target-Aware Transformer CVPR 2022
Perceptual Consistency in Video Segmentation WACV 2022
Learnable Adaptive Cosine Estimator (LACE) for Image Classification WACV 2022
Multi-class AUC Optimization for Robust Small-footprint Keyword Spotting with Limited Training Data INTERSPEECH 2022
Novel Ensemble Diversification Methods for Open-Set Scenarios WACV 2022
A study on constraining Connectionist Temporal Classification for temporal audio alignment INTERSPEECH 2022
Don’t Take It Literally: An Edit-Invariant Sequence Loss for Text Generation NAACL 2022
Improving abstractive summarization with energy-based re-ranking EMNLP 2022
A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network Calibration CVPR 2022