Graph-based Analysis of Hierarchical Embedding Generated by Deep Neural Network - Archive ouverte HAL Access content directly
Conference Papers Year : 2022

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

Abstract

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
Origin : Files produced by the author(s)
Licence : Copyright

Dates and versions

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

Identifiers

  • HAL Id : hal-03981883 , version 1

Cite

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 View
4 Download

Share

Gmail Facebook X LinkedIn More