Training, Architecture, and Prior for Deterministic Uncertainty Methods
Accurate and efficient uncertainty estimation is crucial to build reliable Machine Learning (ML) models capable to provide calibrated uncertainty estimates, generalize and detect Out-Of-Distribution (OOD) datasets. To this end, Deterministic Uncertainty Methods (DUMs) is a promising model family capable to perform uncertainty estimation in a single forward pass. This work investigates important design choices in DUMs: (1) we show that training schemes decoupling the core architecture and the uncertainty head schemes can significantly improve uncertainty performances. (2) we demonstrate that the core architecture expressiveness is crucial for uncertainty performance and that additional architecture constraints to avoid feature collapse can deteriorate the trade-off between OOD generalization and detection. (3) Contrary to other Bayesian models, we show that the prior defined by DUMs do not have a strong effect on the final performances.
Code (1)
Similar Papers 제목 키워드 기반
Invascal: Inverse-Vacuity Self-Calibration for Uncertainty-Aware LiDAR Range-View Semantic Segmentation
LiDAR semantic segmentation is a core perception capability for autonomous vehicles and mobile robots. However, safe operation also depends on knowing when predictions are unreliable. Existing approaches typically rely o…
LIDAR Semantic SegmentationAutonomous VehiclesDeep Deterministic Uncertainty: A Simple Baseline
Reliable uncertainty from deterministic single-forward pass models is sought after because conventional methods of uncertainty quantification are computationally expensive. We take two complex single-forward-pass uncerta…
Active LearningUncertainty QuantificationBayesian Deep Learning for Convective Initiation Nowcasting Uncertainty Estimation
This study evaluated the probability and uncertainty forecasts of five recently proposed Bayesian deep learning methods relative to a deterministic residual neural network (ResNet) baseline for 0-1 h convective initiatio…
Deep Deterministic Uncertainty: A New Simple Baseline
Reliable uncertainty from deterministic single-forward pass models is sought after because conventional methods of uncertainty quantification are computationally expensive. We take two complex single-forward-pass unc…
Active LearningSemantic SegmentationUncertainty QuantificationDiscriminant Distance-Aware Representation on Deterministic Uncertainty Quantification Methods
Uncertainty estimation is a crucial aspect of deploying dependable deep learning models in safety-critical systems. In this study, we introduce a novel and efficient method for deterministic uncertainty estimation called…
Uncertainty Quantification