Emanuel Aldea — accepted AI-conference papers

2026

Fisher-Rao Sensitivity for Out-of-Distribution Detection in Deep Neural Networks

Anthony Nguyen, Antonin Bertrand, Sylvie Le Hégarat-Mascle, Emanuel Aldea, Franck FLORIN, Mohammed Nabil EL-KORSO +1

ICLR 2026poster

Deep neural networks often remain overconfident on Out-of-Distribution (OoD) inputs. We revisit this problem through Riemannian information geometry. We model the network's predictions as a statistical manifold and find that OoD inputs exhibit higher local Fisher-Rao sensitivity. By quantifying this…

Cited by 0 Source ↗Scholar ↗

2025

Stochastic Embeddings : A Probabilistic and Geometric Analysis of Out-of-Distribution Behavior

Anthony Nguyen, Emanuel Aldea, Sylvie Le Hégarat-Mascle, Renaud Lustrat

UAI 2025

Deep neural networks perform well in many applications but often fail when exposed to out-of-distribution (OoD) inputs. We identify a geometric phenomenon in the embedding space: in-distribution (ID) data show higher variance than OoD data under stochastic perturbations. Using high-dimensional geome

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

A Symmetry-Aware Exploration of Bayesian Neural Network Posteriors

Olivier Laurent, Emanuel Aldea, Gianni Franchi

ICLR 2024poster

The distribution of modern deep neural networks (DNNs) weights -- crucial for uncertainty quantification and robustness -- is an eminently complex object due to its extremely high dimensionality. This paper presents one of the first large-scale explorations of the posterior distribution of deep Baye…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗

2024

Discretization-Induced Dirichlet Posterior for Robust Uncertainty Quantification on Regression

Xuanlong Yu, Gianni Franchi, Jindong Gu, Emanuel Aldea

AAAI 2024technical

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 r…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗

2022

Latent Discriminant Deterministic Uncertainty

Gianni Franchi, Xuanlong Yu, Andrei Bursuc, Emanuel Aldea, Severine Dubuisson, David Filliat

ECCV 2022poster

"Predictive uncertainty estimation is essential for deploying Deep Neural Networks in real-world autonomous systems. However, most successful approaches are computationally intensive. In this work, we attempt to address these challenges in the context of autonomous driving perception tasks. Recently…

Cited by 23 Source ↗PDF ↗code ↗Scholar ↗

2020

TRADI: Tracking Deep Neural network Weight Distributions

Gianni Franchi, Andrei Bursuc, Emanuel Aldea, Séverine Dubuisson, Isabelle Bloch

ECCV 2020poster

During training, the weights of a Deep Neural Network (DNN) are optimized from a random initialization towards a nearly optimum value minimizing a loss function. Only this final state of the weights is typically kept for testing, while the wealth of information on the geometry of the weight space, a…

Cited by 51 Source ↗PDF ↗Scholar ↗