Communication Dans Un Congrès Année : 2024

Explaining SAR ATR Models Predictions with Counterfactual Explanations

Résumé

In recent years, Deep Learning models have become more and more popular and their performance have been tested on several domains, from medical to military applications. While being particularly competitive, their non-transparency nature raise plentiful questions, in particular in critical applications for which it seems self-evident to have more insight on models. To alleviate this issue, the eXplainable Artificial Intelligence field has emerged in order to propound more understandable models and consequently to make them more trustworthy. Yet, eXplainable Artificial Intelligence for Synthetic Aperture Radar (SAR) images and especially for Automatic Target Recognition (ATR) is still an emerging subject. In this paper, we investigate the potential of counterfactual explanations to explain ATR model decisions. Not only do we detail the method that we used to generate counterfactual explanations, but we also illustrate how we exploit them to provide semi-global explanations. Thanks to the well-known MSTAR dataset, we effectively show that this approach can unveil how the model imagines a class against another and, more generally, improve the comprehension of the ATR model reasoning.

Fichier non déposé

Dates et versions

hal-05070418 , version 1 (16-05-2025)

Identifiants

Citer

Héloïse Remusati, Jean-Marc Le Caillec, Jean-Yves Schneider, Jacques Petit-Frère, Thomas Merlet. Explaining SAR ATR Models Predictions with Counterfactual Explanations. RADAR 2024: International Radar Conference, Oct 2024, Rennes, France. pp.1-5, ⟨10.1109/RADAR58436.2024.10994132⟩. ⟨hal-05070418⟩
36 Consultations
0 Téléchargements

Altmetric

Partager

  • More