Disentangled representations: towards interpretation of sex determination from hip bone - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue The Visual Computer Année : 2023

Disentangled representations: towards interpretation of sex determination from hip bone

Résumé

Neural network-based classification methods are often criticized for their lack of interpretability and explainability. By highlighting the regions of the input image that contribute the most to the decision, saliency maps have become a popular method to make neural networks interpretable. In medical imaging, they are particularly well-suited for explaining neural networks in the context of abnormality localization. Nevertheless, they seem less suitable for classification problems in which the features that allow distinguishing classes are spatially correlated and scattered. We propose here a novel paradigm based on Disentangled Variational Auto-Encoders. Instead of seeking to understand what the neural network has learned or how prediction is done, we seek to reveal class differences. This is achieved by transforming the sample from a given class into the "same" sample but belonging to another class, thus paving the way to easier interpretation of class differences. Our experiments in the context of automatic sex determination from hip bones show that the obtained results are consistent with expert knowledge. Moreover, the proposed approach enables us to confirm or question the choice of the classifier, or eventually to doubt it.
Fichier principal
Vignette du fichier
zou2023TVCJ.pdf (6.8 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03923993 , version 1 (05-01-2023)

Identifiants

Citer

Kaifeng Zou, Sylvain Faisan, Fabrice Heitz, Marie Epain, P Croisille, et al.. Disentangled representations: towards interpretation of sex determination from hip bone. The Visual Computer, 2023, ⟨10.1007/s00371-022-02755-0⟩. ⟨hal-03923993⟩
26 Consultations
14 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More