paper-with-me

Papers

Training, Architecture, and Prior for Deterministic Uncertainty Methods

2023-03-10 · Bertrand Charpentier, Chenxiang Zhang, Stephan Günnemann

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.

📄 PDF Abstract BibTeX arXiv:2303.05796

Code (1)

orientino/dum-components 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Invascal: Inverse-Vacuity Self-Calibration for Uncertainty-Aware LiDAR Range-View Semantic Segmentation

2026-05-20 · Kerim Turacan, Hannes Reichert, Andrei Bolandut, Konrad Doll arxiv

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 Vehicles

Deep Deterministic Uncertainty: A Simple Baseline

2021-02-23 · Jishnu Mukhoti, Andreas Kirsch, Joost van Amersfoort, Philip H. S. Torr 외

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 Quantification

Bayesian Deep Learning for Convective Initiation Nowcasting Uncertainty Estimation

2025-07-22 · Da Fan, David John Gagne, Steven J. Greybush, Eugene E. Clothiaux 외 arxiv

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

2023-01-01 · CVPR 2023 1 · Jishnu Mukhoti, Andreas Kirsch, Joost van Amersfoort, Philip H.S. Torr 외

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 Quantification

Discriminant Distance-Aware Representation on Deterministic Uncertainty Quantification Methods

2024-02-20 · Jiaxin Zhang, Kamalika Das, Sricharan Kumar

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