Deep Evidential Regression

2019-10-07 · NeurIPS 2020 12 · Alexander Amini, Wilko Schwarting, Ava Soleimany, Daniela Rus

Deterministic neural networks (NNs) are increasingly being deployed in safety critical domains, where calibrated, robust, and efficient measures of uncertainty are crucial. In this paper, we propose a novel method for training non-Bayesian NNs to estimate a continuous target as well as its associated evidence in order to learn both aleatoric and epistemic uncertainty. We accomplish this by placing evidential priors over the original Gaussian likelihood function and training the NN to infer the hyperparameters of the evidential distribution. We additionally impose priors during training such that the model is regularized when its predicted evidence is not aligned with the correct output. Our method does not rely on sampling during inference or on out-of-distribution (OOD) examples for training, thus enabling efficient and scalable uncertainty learning. We demonstrate learning well-calibrated measures of uncertainty on various benchmarks, scaling to complex computer vision tasks, as well as robustness to adversarial and OOD test samples.

📄 PDF Abstract BibTeX arXiv:1910.02600

Code (6)

aamini/evidential-deep-learning 공식 구현 tf

ENSTA-U2IS-AI/torch-uncertainty pytorch

deebuls/deep_evidential_regression_loss_pytorch pytorch

flynnye/ur-ern pytorch

teddykoker/evidential-learning-pytorch pytorch

usccolumbia/materialsuq pytorch

Tasks

regressionUncertainty Quantification

Methods 이 논문이 사용한 방법론

Test 설명 없음

Multivariate Deep Evidential Regression

2021-04-13 · Nis Meinert, Alexander Lavin

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 …

regression

The Unreasonable Effectiveness of Deep Evidential Regression

2022-05-20 · Nis Meinert, Jakob Gawlikowski, Alexander Lavin

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…

regression Uncertainty Quantification

EvCenterNet: Uncertainty Estimation for Object Detection using Evidential Learning

2023-03-06 · Monish R. Nallapareddy, Kshitij Sirohi, Paulo L. J. Drews-Jr, Wolfram Burgard 외

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 Detection Decision Making object-detection Object Detection+1

Evidential Uncertainty Quantification: A Variance-Based Perspective

2023-11-19 · Ruxiao Duan, Brian Caffo, Harrison X. Bai, Haris I. Sair 외

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 Learning Classification Domain Adaptation regression+1

Deep Evidential Uncertainty

2019-09-25 · Alexander Amini, Wilko Schwarting, Ava Soleimany, Daniela Rus

Deterministic neural networks (NNs) are increasingly being deployed in safety critical domains, where calibrated, robust and efficient measures of uncertainty are crucial. While it is possible to train regression network…