Assessment of the Reliablity of a Model's Decision by Generalizing Attribution to the Wavelet Domain - Mines Paris Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Assessment of the Reliablity of a Model's Decision by Generalizing Attribution to the Wavelet Domain

Résumé

Neural networks have shown remarkable performance in computer vision, but their deployment in numerous scientific and technical fields is challenging due to their black-box nature. Scientists and practitioners need to evaluate the reliability of a decision, i.e., to know simultaneously if a model relies on the relevant features and whether these features are robust to image corruptions. Existing attribution methods aim to provide human-understandable explanations by highlighting important regions in the image domain, but fail to fully characterize a decision process's reliability. To bridge this gap, we introduce the Wavelet sCale Attribution Method (WCAM), a generalization of attribution from the pixel domain to the space-scale domain using wavelet transforms. Attribution in the wavelet domain reveals where and on what scales the model focuses, thus enabling us to assess whether a decision is reliable. Our code is accessible here: \url{https://github.com/gabrielkasmi/spectral-attribution}.
Fichier non déposé

Dates et versions

hal-04385590 , version 1 (10-01-2024)

Identifiants

  • HAL Id : hal-04385590 , version 1

Citer

Gabriel Kasmi, Laurent Dubus, Yves-Marie Saint-Drenan, Philippe Blanc. Assessment of the Reliablity of a Model's Decision by Generalizing Attribution to the Wavelet Domain. XAI in Action: Past, Present, and Future Applications, Dec 2023, New Orléans, United States. ⟨hal-04385590⟩
20 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More