SENA: Similarity-based Error-checking of Neural Activations - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

SENA: Similarity-based Error-checking of Neural Activations

Résumé

In this work, we propose SENA, a run-time monitor focused on detecting unreliable predictions from machine learning (ML) classifiers. The main idea is that instead of trying to detect when an image is out-of-distribution (OOD), which will not always result in a wrong output, we focus on detecting if the prediction from the ML model is not reliable, which will most of the time result in a wrong output, independently of whether it is in-distribution (ID) or OOD. The verification is done by checking the similarity between the neural activations of an incoming input and a set of representative neural activations recorded during training. SENA uses information from true-positive and false-negative examples collected during training to verify if a prediction is reliable or not. Our approach achieves results comparable to state-of-the-art solutions without requiring any prior OOD information and without hyperparameter tuning. Besides, the code is publicly available for easy reproducibility at https://github.com/raulsenaferreira/SENA.
Fichier principal
Vignette du fichier
ECAI.pdf (578.67 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04212952 , version 1 (20-09-2023)

Identifiants

  • HAL Id : hal-04212952 , version 1

Citer

Raul Sena Ferreira, Joris Guerin, Jeremie Guiochet, Hélène Waeselynck. SENA: Similarity-based Error-checking of Neural Activations. 27th European Conference on Artificial Intelligence - ECAI 2023, Sep 2023, Krakow, Poland. ⟨hal-04212952⟩
78 Consultations
31 Téléchargements

Partager

Gmail Facebook X LinkedIn More