Communication Dans Un Congrès Année : 2024

General Feature Extraction In SAR Target Classification: A Contrastive Learning Approach Across Sensor Types

Résumé

The increased availability of SAR data has raised a growing interest in applying deep learning algorithms. However, the limited availability of labeled data poses a significant challenge for supervised training. This article introduces a new method for classifying SAR data with minimal labeled images. The method is based on a feature extractor Vit trained with contrastive learning. It is trained on a dataset completely different from the one on which classification is made. The effectiveness of the method is assessed through 2D visualization using t-SNE for qualitative evaluation and k-NN classification with a small number of labeled data for quantitative evaluation. Notably, our results outperform a k-NN on data processed with PCA and a ResNet-34 specifically trained for the task, achieving a 95.9% accuracy on the MSTAR dataset with just ten labeled images per class.

Fichier principal
Vignette du fichier
main.pdf (1) Télécharger le fichier
IGARSS_2024.pdf (1) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04915023 , version 1 (31-01-2025)

Identifiants

Citer

M. Muzeau, J. Frontera-Pons, Chengfang Ren, J.-P. Ovarlez. General Feature Extraction In SAR Target Classification: A Contrastive Learning Approach Across Sensor Types. IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium, Jul 2024, Athens, France. pp.8703-8707, ⟨10.1109/IGARSS53475.2024.10642123⟩. ⟨hal-04915023⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

More