Search Results for author:
Found 5 papers, 1 papers with code
On-manifold Adversarial Data Augmentation Improves Uncertainty Calibration
Uncertainty estimates help to identify ambiguous, novel, or anomalous inputs, but the reliable quantification of uncertainty has proven to be challenging for modern deep networks.
Multi-Class Uncertainty Calibration via Mutual Information Maximization-based Binning
The goal of this paper is to resolve the identified issues of HB in order to provide calibrated confidence estimates using only a small holdout calibration dataset for bin optimization while preserving multi-class ranking accuracy.
Investigation of Uncertainty of Deep Learning-based Object Classification on Radar Spectra
Deep learning (DL) has recently attracted increasing interest to improve object type classification for automotive radar. In addition to high accuracy, it is crucial for decision making in autonomous vehicles to evaluate the reliability of the predictions; however, decisions of DL networks are non-transparent.
Improving Uncertainty of Deep Learning-based Object Classification on Radar Spectra using Label Smoothing
The focus of this article is to learn deep radar spectra classifiers which offer robust real-time uncertainty estimates using label smoothing during training.
Validation of Composite Systems by Discrepancy Propagation
Assessing the validity of a real-world system with respect to given quality criteria is a common yet costly task in industrial applications due to the vast number of required real-world tests.
