Multivariate Deep Evidential Regression
There is significant need for principled uncertainty reasoning in machine learning systems as they are increasingly deployed in safety-critical domains. A new approach with uncertainty-aware neural networks (NNs), based on learning evidential distributions for aleatoric and epistemic uncertainties, shows promise over traditional deterministic methods and typical Bayesian NNs, yet several important gaps in the theory and implementation of these networks remain. We discuss three issues with a proposed solution to extract aleatoric and epistemic uncertainties from regression-based neural networks. The approach derives a technique by placing evidential priors over the original Gaussian likelihood function and training the NN to infer the hyperparameters of the evidential distribution. Doing so allows for the simultaneous extraction of both uncertainties without sampling or utilization of out-of-distribution data for univariate regression tasks. We describe the outstanding issues in detail, provide a possible solution, and generalize the deep evidential regression technique for multivariate cases.
Code (1)
Tasks
regressionSimilar Papers 제목 키워드 기반
ELLIPSE: Evidential Learning for Robust Waypoints and Uncertainties
Robust waypoint prediction is crucial for mobile robots operating in open-world, safety-critical settings. While Imitation Learning (IL) methods have demonstrated great success in practice, they are susceptible to distri…
Trust It or Not: Evidential Uncertainty for Feed-Forward 3D Reconstruction with Trust3R
Geometric foundation models hold promise for unconstrained dense geometry prediction from uncalibrated images. However, in current feed-forward designs, their predicted confidence scores are heuristic, lack probabilistic…
3D ReconstructionThe Unreasonable Effectiveness of Deep Evidential Regression
There is a significant need for principled uncertainty reasoning in machine learning systems as they are increasingly deployed in safety-critical domains. A new approach with uncertainty-aware regression-based neural net…
regressionUncertainty QuantificationEvCenterNet: Uncertainty Estimation for Object Detection using Evidential Learning
Uncertainty estimation is crucial in safety-critical settings such as automated driving as it provides valuable information for several downstream tasks including high-level decision making and path planning. In this wor…
2D Object DetectionDecision Makingobject-detectionObject Detection+1Evidential Uncertainty Quantification: A Variance-Based Perspective
Uncertainty quantification of deep neural networks has become an active field of research and plays a crucial role in various downstream tasks such as active learning. Recent advances in evidential deep learning shed lig…
Active LearningClassificationDomain Adaptationregression+1