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

TL;DR

This paper presents a contrastive learning-based feature extractor for SAR target classification that performs well across sensor types with minimal labeled data, achieving high accuracy on the MSTAR dataset.

Contribution

Introduces a novel contrastive learning approach for SAR feature extraction that generalizes across sensor types with limited labeled data.

Findings

Achieves 95.9% accuracy on MSTAR with only ten labeled images per class.

Outperforms PCA and ResNet-34 in SAR classification tasks.

Effective in cross-sensor scenarios with minimal supervision.

Abstract

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.