Multi Layered Feature Explanation Method for Convolutional Neural Networks ⋆ - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Multi Layered Feature Explanation Method for Convolutional Neural Networks ⋆

Résumé

The most popular methods for Artificial Intelligence such as Deep Neural Networks are, for the vast majority, considered black boxes. It is necessary to explain their decisions to understand the input data which influence most the result. Methods presented in this paper aim at an explanation in image classification tasks: which data in the input are the most important for the result. We further extend the Feature Explanation Method (FEM) from our previous work, transforming it into a multi-layered FEM (MLFEM). The evaluation of the method is designed by comparison of explanation maps with human Gaze Fixation Density maps (GFDM). We show that proposed MLFEM outperforms FEM and popular DNN explanation methods in terms of classical comparison metrics with GFDM.
Fichier principal
Vignette du fichier
MLFEM_Springer.pdf (1.82 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03689004 , version 1 (06-06-2022)

Identifiants

Citer

Luca Bourroux, Jenny Benois-Pineau, Romain Bourqui, Romain Giot. Multi Layered Feature Explanation Method for Convolutional Neural Networks ⋆. International Conference on Pattern Recognition and Artificial Intelligence (ICPRAI), Jun 2022, Paris, France. ⟨10.1007/978-3-031-09037-0_49⟩. ⟨hal-03689004⟩

Collections

CNRS
108 Consultations
95 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More