Graph-based Analysis of Hierarchical Embedding Generated by Deep Neural Network - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Graph-based Analysis of Hierarchical Embedding Generated by Deep Neural Network

Résumé

In a previous work, we have developed a framework for the multimodal and hierarchical classification of images from soil remediation reports. We extended this work using Deep Metric Learning (DML) as an additional training step to improve embeddings quality and obtained 84.24% of weighted F1 score for the level 5th hierarchical level. However, the standard classifier performance metrics are insufficient to explain the decision process reasoning. So far of our knowledge, there are no methods to analyze hierarchical classification algorithms. In this work, we propose a method of graph analysis to describe the embeddings that represent the extended classifier, which we believe properly interprets the obtained results than classification metrics. We illustrate the method of analyzing hierarchical classification algorithms on private dataset, but the method remains generic enough to be used in other contexts.
Fichier principal
Vignette du fichier
W18P05.pdf (24.42 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Licence : Copyright (Tous droits réservés)

Dates et versions

hal-03981883 , version 1 (10-02-2023)

Identifiants

  • HAL Id : hal-03981883 , version 1

Citer

Korlan Rysbayeva, Romain Giot, Nicholas Journet. Graph-based Analysis of Hierarchical Embedding Generated by Deep Neural Network. 2-nd Workshop on Explainable and Ethical AI – ICPR 2022, Aug 2022, Montréal, Canada. ⟨hal-03981883⟩

Collections

CNRS
28 Consultations
4 Téléchargements

Partager

Gmail Facebook X LinkedIn More