Latent Representation Entropy Density for Distribution Shift Detection - Confiance.ai
Communication Dans Un Congrès Année : 2024

Latent Representation Entropy Density for Distribution Shift Detection

Résumé

Distribution shift detection is paramount in safety-critical tasks that rely on Deep Neural Networks (DNNs). The detection task entails deriving a confidence score to assert whether a new input sample aligns with the training data distribution of the DNN model. While DNN predictive uncertainty offers an intuitive confidence measure, exploring uncertainty-based distribution shift detection with simple sample-based techniques has been relatively overlooked in recent years due to computational overhead and lower performance than plain post-hoc methods. This paper proposes using simple sample-based techniques for estimating uncertainty and employing the entropy density from intermediate representations to detect distribution shifts. We demonstrate the effectiveness of our method using standard benchmark datasets for out-of-distribution detection and across different common perception tasks with convolutional neural network architectures. Our scope extends beyond classification, encompassing image-level distribution shift detection for object detection and semantic segmentation tasks. Our results show that our method's performance is comparable to existing \textit{State-of-the-Art} methods while being computationally faster and lighter than other Bayesian approaches, affirming its practical utility. Code is available at https://github.com/CEA-LIST/LaREx.
Fichier principal
Vignette du fichier
417_latent_representation_entropy_.pdf (7.48 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04674980 , version 1 (22-08-2024)

Licence

Copyright (Tous droits réservés)

Identifiants

  • HAL Id : hal-04674980 , version 1

Citer

Fabio Arnez, Daniel Alfonso Montoya Vasquez, Ansgar Radermacher, François Terrier. Latent Representation Entropy Density for Distribution Shift Detection. Conference on Uncertainty in Artificial Intelligence (UAI), Jul 2024, Barcelona, Spain. ⟨hal-04674980⟩
81 Consultations
39 Téléchargements

Partager

More