paper-with-me

Papers

Uncertainty Estimation Using a Single Deep Deterministic Neural Network

2020-03-04 · Joost van Amersfoort, Lewis Smith, Yee Whye Teh, Yarin Gal

We propose a method for training a deterministic deep model that can find and reject out of distribution data points at test time with a single forward pass. Our approach, deterministic uncertainty quantification (DUQ), builds upon ideas of RBF networks. We scale training in these with a novel loss function and centroid updating scheme and match the accuracy of softmax models. By enforcing detectability of changes in the input using a gradient penalty, we are able to reliably detect out of distribution data. Our uncertainty quantification scales well to large datasets, and using a single model, we improve upon or match Deep Ensembles in out of distribution detection on notable difficult dataset pairs such as FashionMNIST vs. MNIST, and CIFAR-10 vs. SVHN.

📄 PDF Abstract BibTeX arXiv:2003.02037

Code (2)

y0ast/deterministic-uncertainty-quantification 공식 구현 pytorch
dsgiitr/ML-Reproducibility-2020-DUQ pytorch

Tasks

Out-of-Distribution DetectionUncertainty Quantification

Methods 이 논문이 사용한 방법론

Deep Ensembles 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Simple and Scalable Epistemic Uncertainty Estimation Using a Single Deep Deterministic Neural Network

2020-01-01 · ICML 2020 1 · Joost van Amersfoort, Lewis Smith, Yee Whye Teh, Yarin Gal

We propose a method for training a deterministic deep model that can find and reject out of distribution data points at test time with a single forward pass. Our approach, deterministic uncertainty quantification (DUQ), …

Uncertainty Quantification

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 th…

Deep Deterministic Uncertainty for Semantic Segmentation

2021-10-29 · Jishnu Mukhoti, Joost van Amersfoort, Philip H. S. Torr, Yarin Gal

We extend Deep Deterministic Uncertainty (DDU), a method for uncertainty estimation using feature space densities, to semantic segmentation. DDU enables quantifying and disentangling epistemic and aleatoric uncertainty i…

SegmentationSemantic Segmentation

Factor-Informed Uncertainty Distillation for Gaze Estimation

2026-07-22 · Mohammadreza Jamalifard, Yaxiong Lei, Javier Fumanal Idocin, Parastoo Azizinezhad 외 arxiv

Deep gaze estimation works well in controlled capture but degrades in unconstrained settings, where systems must reject unreliable predictions. Single-pass uncertainty (e.g., heteroscedastic regression) infers uncertaint…

Gaze Estimation

Deep Evidential Learning for Bayesian Quantile Regression

2023-08-21 · Frederik Boe Hüttel, Filipe Rodrigues, Francisco Câmara Pereira

It is desirable to have accurate uncertainty estimation from a single deterministic forward-pass model, as traditional methods for uncertainty quantification are computationally expensive. However, this is difficult beca…

Disentanglementquantile regressionregressionUncertainty Quantification