paper-with-me

Papers

Torch-Uncertainty: A Deep Learning Framework for Uncertainty Quantification

2025-11-13 · Adrien Lafage, Olivier Laurent, Firas Gabetni, Gianni Franchi arxiv

Deep Neural Networks (DNNs) have demonstrated remarkable performance across various domains, including computer vision and natural language processing. However, they often struggle to accurately quantify the uncertainty of their predictions, limiting their broader adoption in critical real-world applications. Uncertainty Quantification (UQ) for Deep Learning seeks to address this challenge by providing methods to improve the reliability of uncertainty estimates. Although numerous techniques have been proposed, a unified tool offering a seamless workflow to evaluate and integrate these methods remains lacking. To bridge this gap, we introduce Torch-Uncertainty, a PyTorch and Lightning-based framework designed to streamline DNN training and evaluation with UQ techniques and metrics. In this paper, we outline the foundational principles of our library and present comprehensive experimental results that benchmark a diverse set of UQ methods across classification, segmentation, and regression tasks. Our library is available at https://github.com/ENSTA-U2IS-AI/Torch-Uncertainty

📄 PDF Abstract BibTeX arXiv:2511.10282

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Uncertainty Quantification of Locally Nonlinear Dynamical Systems using Neural Networks

2020-08-11 · Subhayan De

Models are often given in terms of differential equations to represent physical systems. In the presence of uncertainty, accurate prediction of the behavior of these systems using the models requires understanding the ef…

Uncertainty Quantification

A framework for benchmarking uncertainty in deep regression

2021-09-10 · Franko Schmähling, Jörg Martin, Clemens Elster

We propose a framework for the assessment of uncertainty quantification in deep regression. The framework is based on regression problems where the regression function is a linear combination of nonlinear functions. Basi…

BenchmarkingregressionUncertainty Quantification

Fortuna: A Library for Uncertainty Quantification in Deep Learning

2023-02-08 · Gianluca Detommaso, Alberto Gasparin, Michele Donini, Matthias Seeger 외

We present Fortuna, an open-source library for uncertainty quantification in deep learning. Fortuna supports a range of calibration techniques, such as conformal prediction that can be applied to any trained neural netwo…

Bayesian InferenceBenchmarkingConformal PredictionDeep Learning+1

Uncertainty in Extreme Multi-label Classification

2022-10-18 · Jyun-Yu Jiang, Wei-Cheng Chang, Jiong Zhong, Cho-Jui Hsieh 외

Uncertainty quantification is one of the most crucial tasks to obtain trustworthy and reliable machine learning models for decision making. However, most research in this domain has only focused on problems with small la…

ClassificationDecision MakingExtreme Multi-Label ClassificationMulti-Label Classification+4

A Survey on Uncertainty Toolkits for Deep Learning

2022-05-02 · Maximilian Pintz, Joachim Sicking, Maximilian Poretschkin, Maram Akila

The success of deep learning (DL) fostered the creation of unifying frameworks such as tensorflow or pytorch as much as it was driven by their creation in return. Having common building blocks facilitates the exchange of…

Deep LearningSurveyUncertainty Quantification