Search Results for author: Kanil Patel

Found 5 papers, 1 papers with code

Validation of Composite Systems by Discrepancy Propagation

no code implementations21 Oct 2022 David Reeb, Kanil Patel, Karim Barsim, Martin Schiegg, Sebastian Gerwinn

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.

Experimental Design valid

Improving Uncertainty of Deep Learning-based Object Classification on Radar Spectra using Label Smoothing

no code implementations27 Sep 2021 Kanil Patel, William Beluch, Kilian Rambach, Michael Pfeiffer, Bin Yang

The focus of this article is to learn deep radar spectra classifiers which offer robust real-time uncertainty estimates using label smoothing during training.

Decision Making

Investigation of Uncertainty of Deep Learning-based Object Classification on Radar Spectra

no code implementations1 Jun 2021 Kanil Patel, William Beluch, Kilian Rambach, Adriana-Eliza Cozma, Michael Pfeiffer, Bin Yang

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.

Autonomous Vehicles Decision Making +3

Multi-Class Uncertainty Calibration via Mutual Information Maximization-based Binning

1 code implementation ICLR 2021 Kanil Patel, William Beluch, Bin Yang, Michael Pfeiffer, Dan Zhang

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.

Quantization

On-manifold Adversarial Data Augmentation Improves Uncertainty Calibration

no code implementations16 Dec 2019 Kanil Patel, William Beluch, Dan Zhang, Michael Pfeiffer, Bin Yang

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.

Adversarial Attack Data Augmentation

Cannot find the paper you are looking for? You can Submit a new open access paper.