Towards building self-aware object detectors via reliable uncertainty quantification and calibration
The current approach for testing the robustness of object detectors suffers from serious
deficiencies such as improper methods of performing out-of-distribution detection and using …
deficiencies such as improper methods of performing out-of-distribution detection and using …
Prediction uncertainty validation for computational chemists
P Pernot - The Journal of Chemical Physics, 2022 - pubs.aip.org
Validation of prediction uncertainty (PU) is becoming an essential task for modern
computational chemistry. Designed to quantify the reliability of predictions in meteorology …
computational chemistry. Designed to quantify the reliability of predictions in meteorology …
Uncertainty quantification by direct propagation of shallow ensembles
M Kellner, M Ceriotti - Machine Learning: Science and …, 2024 - iopscience.iop.org
Statistical learning algorithms provide a generally-applicable framework to sidestep time-
consuming experiments, or accurate physics-based modeling, but they introduce a further …
consuming experiments, or accurate physics-based modeling, but they introduce a further …
MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection
We propose an extremely simple and highly effective approach to faithfully combine different
object detectors to obtain a Mixture of Experts (MoE) that has a superior accuracy to the …
object detectors to obtain a Mixture of Experts (MoE) that has a superior accuracy to the …
Multi-fidelity Gaussian process surrogate modeling for regression problems in physics
One of the main challenges in surrogate modeling is the limited availability of data due to
resource constraints associated with computationally expensive simulations. Multi-fidelity …
resource constraints associated with computationally expensive simulations. Multi-fidelity …
[PDF][PDF] Trustworthy Bayesian Perceptrons,”
M Walker, H Amirkhanian, MF Huber… - Proceedings of the 27th …, 2024 - isas.iar.kit.edu
Bayesian Neural Networks (BNNs) offer a sophisticated framework for extending classical
neural network point estimates to encompass predictive distributions. Despite the high …
neural network point estimates to encompass predictive distributions. Despite the high …
Sensor Fusion using Probabilistic Object Detection for State Estimation
S Subedi, L Höhndorf, R Kulaga, Z Hodaie… - AIAA AVIATION 2023 …, 2023 - arc.aiaa.org
View Video Presentation: https://doi. org/10.2514/6.2023-3561. vid Kalman filtering for
global navigation satellite systems (GNSS)-aided inertial navigation has been widely used …
global navigation satellite systems (GNSS)-aided inertial navigation has been widely used …
Information Leakage Detection through Approximate Bayes-optimal Prediction
In today's data-driven world, the proliferation of publicly available information intensifies the
challenge of information leakage (IL), raising security concerns. IL involves unintentionally …
challenge of information leakage (IL), raising security concerns. IL involves unintentionally …
Uncertainty Calibration and its Application to Object Detection
F Küppers - arXiv preprint arXiv:2302.02622, 2023 - arxiv.org
Image-based environment perception is an important component especially for driver
assistance systems or autonomous driving. In this scope, modern neuronal networks are …
assistance systems or autonomous driving. In this scope, modern neuronal networks are …
Identifying Trust Regions of Bayesian Neural Networks
M Walker, M Reith-Braun, P Schichtel… - … Sensor Data Fusion …, 2023 - ieeexplore.ieee.org
Bayesian neural networks (BNNs) offer an elegant and promising approach to deciding
whether the predictions of a neural network are trustworthy by allowing the estimation of …
whether the predictions of a neural network are trustworthy by allowing the estimation of …