RefCal uses a supervised contrastive loss to promote refinement alongside calibration in DNN training, reporting better accuracy, refinement, and ECE than baselines on imbalanced CIFAR-100-LT.
Hendryckset al.Hendrycks & Dietterich (2018) benchmark robustness of aDNNusing15algo- rithmically generated image corruptions that mimic natural corruptions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Enhancing Deep Neural Network Reliability with Refinement and Calibration
RefCal uses a supervised contrastive loss to promote refinement alongside calibration in DNN training, reporting better accuracy, refinement, and ECE than baselines on imbalanced CIFAR-100-LT.