Discretization-Induced Dirichlet Posterior for Robust Uncertainty Quantification on Regression - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

Discretization-Induced Dirichlet Posterior for Robust Uncertainty Quantification on Regression

Résumé

Uncertainty quantification is critical for deploying deep neural networks (DNNs) in real-world applications. An Auxiliary Uncertainty Estimator (AuxUE) is one of the most effective means to estimate the uncertainty of the main task prediction without modifying the main task model. To be considered robust, an AuxUE must be capable of maintaining its performance and triggering higher uncertainties while encountering Out-of-Distribution (OOD) inputs, i.e., to provide robust aleatoric and epistemic uncertainty. However, for vision regression tasks, current AuxUE designs are mainly adopted for aleatoric uncertainty estimates, and AuxUE robustness has not been explored. In this work, we propose a generalized AuxUE scheme for more robust uncertainty quantification on regression tasks. Concretely, to achieve a more robust aleatoric uncertainty estimation, different distribution assumptions are considered for heteroscedastic noise, and Laplace distribution is finally chosen to approximate the prediction error. For epistemic uncertainty, we propose a novel solution named Discretization-Induced Dirichlet pOsterior (DIDO), which models the Dirichlet posterior on the discretized prediction error. Extensive experiments on age estimation, monocular depth estimation, and super-resolution tasks show that our proposed method can provide robust uncertainty estimates in the face of noisy inputs and that it can be scalable to both image-level and pixel-wise tasks.
Fichier principal
Vignette du fichier
2308.09065.pdf (14.99 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04480649 , version 1 (19-04-2024)

Identifiants

Citer

Xuanlong Yu, Gianni Franchi, Jindong Gu, Emanuel Aldea. Discretization-Induced Dirichlet Posterior for Robust Uncertainty Quantification on Regression. 38th AAAI Conference on Artificial Intelligence (AAAI-24), Feb 2024, Vancouvert, Canada. ⟨10.48550/arXiv.2308.09065⟩. ⟨hal-04480649⟩
15 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More