Generative Adversarial Networks for SAR Automatic Target Recognition and Classification Models Enhanced Explainability: Perspectives and Challenges

Remusati, Héloïse; Le Caillec, Jean-Marc; Schneider, Jean-Yves; Petit-Frère, Jacques; Merlet, Thomas

doi:10.3390/rs16142569

Open AccessReview

Generative Adversarial Networks for SAR Automatic Target Recognition and Classification Models Enhanced Explainability: Perspectives and Challenges

by

Héloïse Remusati

^1,*,†

,

Jean-Marc Le Caillec

^2,†

,

Jean-Yves Schneider

¹,

Jacques Petit-Frère

¹ and

Thomas Merlet

¹

Thales LAS France SAS, 2 Avenue Gay Lussac, 78990 Elancourt, France

²

IMT Atlantique Bretagne-Pays de la Loire, Campus de Brest, Technopole Brest-Iroise, CS 83818, CEDEX 3, 29238 Brest, France

^*

Author to whom correspondence should be addressed.

^†

These authors contributed equally to this work.

Remote Sens. 2024, 16(14), 2569; https://doi.org/10.3390/rs16142569

Submission received: 4 June 2024 / Revised: 3 July 2024 / Accepted: 8 July 2024 / Published: 13 July 2024

(This article belongs to the Special Issue Advances in Radar Imaging with Deep Learning Algorithms)

Download

Browse Figures

Versions Notes

Abstract

Generative adversarial networks (or GANs) are a specific deep learning architecture often used for different usages, such as data generation or image-to-image translation. In recent years, this structure has gained increased popularity and has been used in different fields. One area of expertise currently in vogue is the use of GANs to produce synthetic aperture radar (SAR) data, and especially expand training datasets for SAR automatic target recognition (ATR). In effect, the complex SAR image formation makes these kind of data rich in information, leading to the use of deep networks in deep learning-based methods. Yet, deep networks also require sufficient data for training. However, contrary to optical images, we generally do not have a substantial number of available SAR images because of their acquisition and labelling cost; GANs are then an interesting tool. Concurrently, how to improve explainability for SAR ATR deep neural networks and how to make their reasoning more transparent have been increasingly explored as model opacity deteriorates trust of users. This paper aims at reviewing how GANs are used with SAR images, but also giving perspectives on how GANs could be used to improve interpretability and explainability of SAR classifiers.

Keywords: explanation; neural networks; radar target recognition; synthetic aperture radar

Share and Cite

MDPI and ACS Style

Remusati, H.; Le Caillec, J.-M.; Schneider, J.-Y.; Petit-Frère, J.; Merlet, T. Generative Adversarial Networks for SAR Automatic Target Recognition and Classification Models Enhanced Explainability: Perspectives and Challenges. Remote Sens. 2024, 16, 2569. https://doi.org/10.3390/rs16142569

AMA Style

Remusati H, Le Caillec J-M, Schneider J-Y, Petit-Frère J, Merlet T. Generative Adversarial Networks for SAR Automatic Target Recognition and Classification Models Enhanced Explainability: Perspectives and Challenges. Remote Sensing. 2024; 16(14):2569. https://doi.org/10.3390/rs16142569

Chicago/Turabian Style

Remusati, Héloïse, Jean-Marc Le Caillec, Jean-Yves Schneider, Jacques Petit-Frère, and Thomas Merlet. 2024. "Generative Adversarial Networks for SAR Automatic Target Recognition and Classification Models Enhanced Explainability: Perspectives and Challenges" Remote Sensing 16, no. 14: 2569. https://doi.org/10.3390/rs16142569

APA Style

Remusati, H., Le Caillec, J.-M., Schneider, J.-Y., Petit-Frère, J., & Merlet, T. (2024). Generative Adversarial Networks for SAR Automatic Target Recognition and Classification Models Enhanced Explainability: Perspectives and Challenges. Remote Sensing, 16(14), 2569. https://doi.org/10.3390/rs16142569

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Generative Adversarial Networks for SAR Automatic Target Recognition and Classification Models Enhanced Explainability: Perspectives and Challenges

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI