← Search

Bingyuan Liu

2 accepted papers

2023

Class Adaptive Network Calibration

CVPR 2023poster

Recent studies have revealed that, beyond conventional accuracy, calibration should also be considered for training modern deep neural networks. To address miscalibration during learning, some methods have explored different penalty functions as part of the learning objective, alongside a standard c…

2022

The Devil Is in the Margin: Margin-Based Label Smoothing for Network Calibration

CVPR 2022poster

In spite of the dominant performances of deep neural networks, recent works have shown that they are poorly calibrated, resulting in over-confident predictions. Miscalibration can be exacerbated by overfitting due to the minimization of the cross-entropy during training, as it promotes the predicted…

Cited by 94PDFcodeScholar